Showing 1–25 of 40 results for all: fog rendering

The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators

Authors: Thomas Deixelberger, Markus Steinberger

Abstract: Clearing fog, rain or snow from footage, or turning… ▽ More Clearing fog, rain or snow from footage, or turning renders into photographs, must remove the source domain and keep the scene. Unpaired translators carry it through because their generator sees the source appearance (pixels, a near-invertible latent or a control map) and keeps it. A DINO feature map fixes what is in the scene and carries weather, lighting and rendering style as a residue of 13 to 14% of the feature norm. We propose the Representation Feature Adapter (RFA), a 2.9M-parameter network that moves this residue. We train only the adapter and its discriminators; the encoder and a feature-conditioned decoder, trained once for all conditions, stay frozen. Against CycleGAN-Turbo it is ahead on both metrics on fog and on KID on night, and level within noise on snow, rain and haze. On sim-to-real it leads REGEN and HyPER-GAN on both metrics. Only the RFA removes the rain while keeping the scene. The removal costs scene structure: CycleGAN-Turbo keeps more on every condition but fog. On VAE latents the identical adapter collapses to the identity, and decoders from other groups that never saw it render its output. The RFA has about 160 times fewer trainable parameters than CycleGAN-Turbo and under a fifth of its per-condition training time. △ Less

Submitted 29 September, 2026; originally announced September 2026.

Comments: 9 pages main text, 28 pages including appendix. 12 figures, 13 tables

ACM Class: I.2.10; I.4.3; I.4.8

Beyond Clear Skies: Synthetic Seasonal and Weather Variations for Real-World Drone Detection

Authors: Tamara R. Lenhard, Andreas Weinmann, Tobias Koch

Abstract: …conditions. Conversely, synthetic data offers a scalable alternative: environmental variation becomes controllable, while modern game-engine-based pipelines provide realistic rendering and automatic annotations. Leveraging this potential, we introduce SynDroneVision-Weather (SDV-W), an systematic extension of SynDroneVision (SDV) targeting adverse-weather an… ▽ More Reliable drone detection under real-world deployment conditions requires training data that spans the full operational design domain, including adverse weather and seasonal appearance variation. However, acquiring and annotating such data at scale remains highly resource-intensive, as adverse-weather conditions are inherently difficult to control, reproduce, and sample systematically. Existing datasets therefore typically provide only limited coverage of such conditions. Conversely, synthetic data offers a scalable alternative: environmental variation becomes controllable, while modern game-engine-based pipelines provide realistic rendering and automatic annotations. Leveraging this potential, we introduce SynDroneVision-Weather (SDV-W), an systematic extension of SynDroneVision (SDV) targeting adverse-weather and seasonal domain shifts in urban drone detection. SDV-W comprises 55,187 annotated high-resolution images from three urban environments, rendered across three seasonal configurations and diverse weather conditions, including rain, snow, and fog at multiple severity levels. By preserving SDV's scene and trajectory configuration, SDV-W enables matched clean-adverse comparisons and quantification of condition-specific detector degradation. Across representative YOLO models and real-world datasets, we show that SDV-W improves detector reliability under adverse appearance shifts, reduces missed detections and false alarms, and is most effective as a complement to general-purpose synthetic drone-detection data. SDV-W will be publicly released upon paper acceptance. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Ensuring Logic in the Fog: Sound POMDP Synthesis with LTL Objectives

Authors: Can Zhou, Yulong Gao, Pian Yu

Abstract: …a rigorous language for specifying such tasks, the inherent undecidability of qualitatively verifying LTL satisfaction in partially observable Markov decision processes renders quantitative synthesis difficult, especially when designing reliable reward signals for approximate solvers. In this paper, we bridge this gap with a novel, sound reward-shaping mecha… ▽ More Synthesising autonomous agents that can navigate uncertain environments while adhering to complex temporal constraints remains a fundamental challenge. While Linear Temporal Logic (LTL) provides a rigorous language for specifying such tasks, the inherent undecidability of qualitatively verifying LTL satisfaction in partially observable Markov decision processes renders quantitative synthesis difficult, especially when designing reliable reward signals for approximate solvers. In this paper, we bridge this gap with a novel, sound reward-shaping mechanism that dynamically generates belief-dependent rewards grounded in certified LTL satisfaction. By integrating this mechanism into an enhanced Monte Carlo Planning framework, we empower agents to navigate the `fog' of partial observability with a search process focused on maximising verifiable success. Our experiments demonstrate that this approach not only thrives in scenarios where existing solvers fail but also maintains effectiveness and scalability across diverse benchmark domains. △ Less

Submitted 12 May, 2026; originally announced May 2026.

Comments: Accepted by IJCAI-ECAI 2026, the 35th International Joint Conference on Artificial Intelligence

Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models

Authors: Yuchen Guo, Junli Gong, Wenjun Dong, Yiuming Cheung, Weifeng Su

Abstract: Purely RGB-based vision models often fail to provide reliable cues in challenging scenarios such as nighttime and fog, leading to degraded performance and safety risks. Infrared imaging captures heat-emitting sources and provides critical complementary information, but existing high-fidelity fusion methods suffer from prohibitive latency,… ▽ More Purely RGB-based vision models often fail to provide reliable cues in challenging scenarios such as nighttime and fog, leading to degraded performance and safety risks. Infrared imaging captures heat-emitting sources and provides critical complementary information, but existing high-fidelity fusion methods suffer from prohibitive latency, rendering them impractical for real-time edge deployment. To address this, we propose FusionProxy, a real-time image fusion module designed as a fully independent, plug-and-play component with diffusion level quality. FusionProxy exploits two complementary statistics of a teacher sample ensemble: per-pixel variance in raw image space, used to weight pixel-level supervision, and per-pixel variance inside frozen foundation backbones, used to route feature-level alignment spatially. Once trained, FusionProxy can be directly integrated into any visual perception system without joint optimization. Extensive experiments demonstrate that our method achieves superior performance on static recognition tasks and significantly enhances robustness in dynamic tasks, including closed-loop autonomous driving. Crucially, FusionProxy achieves real-time inference speeds on diverse platforms, from high-end GPUs to commodity hardware, providing a flexible and generalizable solution for all-day perception. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Neural Surface and Reflectance Modelling from 3D Radar Data

Authors: Judith Treffler, Vladimír Kubelka, Henrik Andreasson, Martin Magnusson

Abstract: …in challenging low-visibility environments. In these conditions, radar has a clear advantage over cameras and lidars due to its resilience to environmental factors such as fog, smoke, or dust. However, radar data is inherently sparse and noisy, making reliable 3D surface reconstruction challenging. To address this, we propose a neural implicit approach for 3… ▽ More Robust scene representation is essential for autonomous systems to safely operate in challenging low-visibility environments. In these conditions, radar has a clear advantage over cameras and lidars due to its resilience to environmental factors such as fog, smoke, or dust. However, radar data is inherently sparse and noisy, making reliable 3D surface reconstruction challenging. To address this, we propose a neural implicit approach for 3D mapping from radar point clouds that jointly models scene geometry and view-dependent radar intensities. Our method leverages a memory-efficient hybrid feature encoding to learn a continuous Signed Distance Field (SDF) for surface reconstruction, while also capturing radar-specific reflective properties. We show that our approach produces smoother, more accurate 3D surface reconstructions compared to existing lidar-based reconstruction methods applied to radar data and can reconstruct view-dependent radar intensities. We also show that, in general, as input point clouds get sparser, neural implicit representations render more faithful surfaces than traditional explicit SDFs and meshing techniques. △ Less

Submitted 20 July, 2026; v1 submitted 26 March, 2026; originally announced March 2026.

Comments: Accepted for publication at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026

TRGS-SLAM: IMU-Aided Gaussian Splatting SLAM for Blurry, Rolling Shutter, and Noisy Thermal Images

Authors: Spencer Carmichael, Katherine A. Skinner

Abstract: …mobile robots: they provide a passive, low-power solution to operating in darkness, are invariant to rapidly changing or high dynamic range illumination, and can see through fog, dust, and smoke. However, uncooled microbolometer thermal cameras, the only practical option in most robotics applications, suffer from significant motion blur, rolling shutter dist… ▽ More Thermal cameras offer several advantages for simultaneous localization and mapping (SLAM) with mobile robots: they provide a passive, low-power solution to operating in darkness, are invariant to rapidly changing or high dynamic range illumination, and can see through fog, dust, and smoke. However, uncooled microbolometer thermal cameras, the only practical option in most robotics applications, suffer from significant motion blur, rolling shutter distortions, and fixed pattern noise. In this paper, we present TRGS-SLAM, a 3D Gaussian Splatting (3DGS) based thermal inertial SLAM system uniquely capable of handling these degradations. To overcome the challenges of thermal data, we introduce a model-aware 3DGS rendering method and several general innovations to 3DGS SLAM, including B-spline trajectory optimization with a two-stage IMU loss, view-diversity-based opacity resetting, and pose drift correction schemes. Our system demonstrates accurate tracking on real-world, fast motion, and high-noise thermal data that causes all other tested SLAM methods to fail. Moreover, through offline refinement of our SLAM results, we demonstrate thermal image restoration competitive with prior work that required ground truth poses. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Comments: Project page: https://umautobots.github.io/trgs_slam

Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark

Authors: Sourav Panda, Tanmay Ambadkar, Shreyash Kale, Abhinav Verma, Jonathan Dodge

Abstract: The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy, but in mini-games simple agents saturate performance. This complexity gap hinders steady curriculum design and prevents researchers from experimenting with modern Reinforceme… ▽ More The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy, but in mini-games simple agents saturate performance. This complexity gap hinders steady curriculum design and prevents researchers from experimenting with modern Reinforcement Learning algorithms in RTS environments under realistic compute budgets. To fill this gap, we present the Two-Bridge Map Suite, the first entry in an open-source benchmark series we purposely engineered as an intermediate benchmark to sit between these extremes. By disabling economy mechanics such as resource collection, base building, and fog-of-war, the environment isolates two core tactical skills: long-range navigation and micro-combat. Preliminary experiments show that agents learn coherent maneuvering and engagement behaviors without imposing full-game computational costs. Two-Bridge is released as a lightweight, Gym-compatible wrapper on top of PySC2, with maps, wrappers, and reference scripts fully open-sourced to encourage broad adoption as a standard benchmark. △ Less

Submitted 21 June, 2026; v1 submitted 18 February, 2026; originally announced March 2026.

Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenance

Authors: Rebin Saleh, Khanh Pham Dinh, Balázs Villányi, Truong-Son Hy

Abstract: …rely on static, offline-trained models that cannot adapt to evolving operational conditions, while LLM-based monolithic systems demand prohibitive memory and latency, rendering them impractical for on-site edge deployment. We introduce SEMAS, a self-evolving hierarchical multi-agent system that distributes specialized agents across Edge,… ▽ More Industrial IoT predictive maintenance requires systems capable of real-time anomaly detection without sacrificing interpretability or demanding excessive computational resources. Traditional approaches rely on static, offline-trained models that cannot adapt to evolving operational conditions, while LLM-based monolithic systems demand prohibitive memory and latency, rendering them impractical for on-site edge deployment. We introduce SEMAS, a self-evolving hierarchical multi-agent system that distributes specialized agents across Edge, Fog, and Cloud computational tiers. Edge agents perform lightweight feature extraction and pre-filtering; Fog agents execute diversified ensemble detection with dynamic consensus voting; and Cloud agents continuously optimize system policies via Proximal Policy Optimization (PPO) while maintaining asynchronous, non-blocking inference. The framework incorporates LLM-based response generation for explainability and federated knowledge aggregation for adaptive policy distribution. This architecture enables resource-aware specialization without sacrificing real-time performance or model interpretability. Empirical evaluation on two industrial benchmarks (Boiler Emulator and Wind Turbine) demonstrates that SEMAS achieves superior anomaly detection performance with exceptional stability under adaptation, sustains prediction accuracy across evolving operational contexts, and delivers substantial latency improvements enabling genuine real-time deployment. Ablation studies confirm that PPO-driven policy evolution, consensus voting, and federated aggregation each contribute materially to system effectiveness. These findings indicate that resource-aware, self-evolving 1multi-agent coordination is essential for production-ready industrial IoT predictive maintenance under strict latency and explainability constraints. △ Less

Submitted 17 February, 2026; originally announced February 2026.

mitransient: Transient light transport in Mitsuba 3

Authors: Diego Royo, Jorge Garcia-Pueyo, Miguel Crespo, Guillermo Enguita, Óscar Pueyo-Ciutad, Diego Bielsa

Abstract: mitransient is a light transport simulation tool that extends Mitsuba 3 with support for time-resolved simulations. In essence, mitransient extends conventional rendering by adding a temporal dimension which accounts for the time of flight of light. This allows rapid prototyping of novel transient imaging systems without the need of costly or difficult-to-op… ▽ More mitransient is a light transport simulation tool that extends Mitsuba 3 with support for time-resolved simulations. In essence, mitransient extends conventional rendering by adding a temporal dimension which accounts for the time of flight of light. This allows rapid prototyping of novel transient imaging systems without the need of costly or difficult-to-operate hardware. Our code is trivially easy to install through pip, and consists of Python modules that can run both in CPU and GPU by leveraging the JIT capabilities of Mitsuba 3. It provides physically-based simulations of complex phenomena, including a wide variety of realistic materials and participating media such as fog or smoke. In addition, we extend Mitsuba 3's functionality to support time-resolved polarization tracking of light and transient differentiable rendering. Finally, we also include tools that simplify the use of our simulations for non-line-of-sight imaging, enabling realistic scene setups with capture noise to be simulated in just seconds of minutes. Altogether, we hope that mitransient will support the research community in developing novel algorithms for transient imaging. △ Less

Submitted 9 March, 2026; v1 submitted 29 October, 2025; originally announced October 2025.

Comments: 6 pages, 6 figures. For further documentation for mitransient see https://mitransient.readthedocs.io

ACM Class: I.3.6; I.3.7

LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering

Authors: Xiaohang Zhan, Dingming Liu

Abstract: …methods provide control over object locations, they fail to address occlusion relationships explicitly. Given a pre-trained image diffusion model, our method leverages volume rendering principles to "… ▽ More We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often lack precision. While layout-to-image methods provide control over object locations, they fail to address occlusion relationships explicitly. Given a pre-trained image diffusion model, our method leverages volume rendering principles to "render" the scene in latent space, guided by occlusion relationships and the estimated transmittance of objects. This approach does not require retraining or fine-tuning the image diffusion model, yet it enables accurate occlusion control due to its physics-grounded foundation. In extensive experiments, our method significantly outperforms existing approaches in terms of occlusion accuracy. Furthermore, we demonstrate that by adjusting the opacities of objects or concepts during rendering, our method can achieve a variety of effects, such as altering the transparency of objects, the density of mass (e.g., forests), the concentration of particles (e.g., rain, fog), the intensity of light, and the strength of lens effects, etc. △ Less

Submitted 11 August, 2025; originally announced August 2025.

Comments: Accepted by ICCV 2025 (oral). Project page: https://xiaohangzhan.github.io/projects/larender/

Fog Intelligence for Network Anomaly Detection

Authors: Kai Yang, Hui Ma, Shaoyu Dou

Abstract: …with many sources of uncertainty that cannot be accurately characterized by traditional mathematical models. However, most machine learning algorithms are centralized, which renders them inapplicable to a large-scale distributed wireless networks with tens of millions of mobile devices. In this article, we present fog… ▽ More Anomalies are common in network system monitoring. When manifested as network threats to be mitigated, service outages to be prevented, and security risks to be ameliorated, detecting such anomalous network behaviors becomes of great importance. However, the growing scale and complexity of the mobile communication networks, as well as the ever-increasing amount and dimensionality of the network surveillance data, make it extremely difficult to monitor a mobile network and discover abnormal network behaviors. Recent advances in machine learning allow for obtaining near-optimal solutions to complicated decision-making problems with many sources of uncertainty that cannot be accurately characterized by traditional mathematical models. However, most machine learning algorithms are centralized, which renders them inapplicable to a large-scale distributed wireless networks with tens of millions of mobile devices. In this article, we present fog intelligence, a distributed machine learning architecture that enables intelligent wireless network management. It preserves the advantage of both edge processing and centralized cloud computing. In addition, the proposed architecture is scalable, privacy-preserving, and well suited for intelligent management of a distributed wireless network. △ Less

Submitted 26 May, 2025; originally announced May 2025.

Comments: published in IEEE Network

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field

Authors: Chenghao Qian, Wenjing Li, Yuhu Guo, Gustav Markkula

Abstract: …To construct the weather particles, we first reconstruct a 3D scene using the edited images and then introduce a dynamic 4D Gaussian field to generate snowflakes, raindrops and fog in the scene. The attributes and dynamics of these particles are precisely controlled through physical-based modelling and simulation, ensuring realistic weather representation a… ▽ More In this work, we present WeatherEdit, a novel weather editing pipeline for generating realistic weather effects with controllable types and severity in 3D scenes. Our approach is structured into two key components: weather background editing and weather particle construction. For weather background editing, we introduce an all-in-one adapter that integrates multiple weather styles into a single pretrained diffusion model, enabling the generation of diverse weather effects in 2D image backgrounds. During inference, we design a Temporal-View (TV-) attention mechanism that follows a specific order to aggregate temporal and spatial information, ensuring consistent editing across multi-frame and multi-view images. To construct the weather particles, we first reconstruct a 3D scene using the edited images and then introduce a dynamic 4D Gaussian field to generate snowflakes, raindrops and fog in the scene. The attributes and dynamics of these particles are precisely controlled through physical-based modelling and simulation, ensuring realistic weather representation and flexible severity adjustments. Finally, we integrate the 4D Gaussian field with the 3D scene to render consistent and highly realistic weather effects. Experiments on multiple driving datasets demonstrate that WeatherEdit can generate diverse weather effects with controllable condition severity, highlighting its potential for autonomous driving simulation in adverse weather. See project page: https://jumponthemoon.github.io/w-edit △ Less

Submitted 7 August, 2025; v1 submitted 26 May, 2025; originally announced May 2025.

DehazeGS: Seeing Through Fog with 3D Gaussian Splatting

Authors: Jinze Yu, Yiqun Wang, Aiheng Jiang, Zhengda Lu, Jianwei Guo, Yong Li, Hongxing Qin, Xiaopeng Zhang

Abstract: …synthesis methods are typically designed for high-quality and clean input images. However, in foggy scenes, scattering and attenuation can significantly degrade the quality of rendering. Although NeRF-based dehazing approaches have been developed, their reliance on deep fully connected neural networks and per-ray sampling strategies leads to high computation… ▽ More Current novel view synthesis methods are typically designed for high-quality and clean input images. However, in foggy scenes, scattering and attenuation can significantly degrade the quality of rendering. Although NeRF-based dehazing approaches have been developed, their reliance on deep fully connected neural networks and per-ray sampling strategies leads to high computational costs. Furthermore, NeRF's implicit representation limits its ability to recover fine-grained details from hazy scenes. To overcome these limitations, we propose learning an explicit Gaussian representation to explain the formation mechanism of foggy images through a physically forward rendering process. Our method, DehazeGS, reconstructs and renders fog-free scenes using only multi-view foggy images as input. Specifically, based on the atmospheric scattering model, we simulate the formation of fog by establishing the transmission function directly onto Gaussian primitives via depth-to-transmission mapping. During training, we jointly learn the atmospheric light and scattering coefficients while optimizing the Gaussian representation of foggy scenes. At inference time, we remove the effects of scattering and attenuation in Gaussian distributions and directly render the scene to obtain dehazed views. Experiments on both real-world and synthetic foggy datasets demonstrate that DehazeGS achieves state-of-the-art performance. visualizations are available at https://jz-y-cn.github.io/DehazeGS/ △ Less

Submitted 30 July, 2026; v1 submitted 7 January, 2025; originally announced January 2025.

Comments: 9 pages,5 figures. Accepted by AAAI2026. visualizations are available at https://jz-y-cn.github.io/DehazeGS/

Optimized Quality of Service prediction in FSO Links over South Africa using Ensemble Learning

Authors: S. O. Adebusola, P. A. Owolawi, J. S. Ojo, P. S. Maswikaneng

Abstract: …by harsh weather situations like mist, precipitation, blizzard, fume, soil, and drizzle debris in the atmosphere, all of which have an impact on the Quality of Service (QoS) rendered by the systems. The primary goal of this article is to optimize the QoS using the ensemble learning models Random Forest, ADaBoost Regression, Stacking Regression, Gradient Boos… ▽ More Fibre optic communication system is expected to increase exponentially in terms of application due to the numerous advantages over copper wires. The optical network evolution presents several advantages such as over long-distance, low-power requirement, higher carrying capacity and high bandwidth among others Such network bandwidth surpasses methods of transmission that include copper cables and microwaves. Despite these benefits, free-space optical communications are severely impacted by harsh weather situations like mist, precipitation, blizzard, fume, soil, and drizzle debris in the atmosphere, all of which have an impact on the Quality of Service (QoS) rendered by the systems. The primary goal of this article is to optimize the QoS using the ensemble learning models Random Forest, ADaBoost Regression, Stacking Regression, Gradient Boost Regression, and Multilayer Neural Network. To accomplish the stated goal, meteorological data, visibility, wind speed, and altitude were obtained from the South Africa Weather Services archive during a ten-year period (2010 to 2019) at four different locations: Polokwane, Kimberley, Bloemfontein, and George. We estimated the data rate, power received, fog-induced attenuation, bit error rate and power penalty using the collected and processed data. The RMSE and R-squared values of the model across all the study locations, Polokwane, Kimberley, Bloemfontein, and George, are 0.0073 and 0.9951, 0.0065 and 0.9998, 0.0060 and 0.9941, and 0.0032 and 0.9906, respectively. The result showed that using ensemble learning techniques in transmission modeling can significantly enhance service quality and meet customer service level agreements and ensemble method was successful in efficiently optimizing the signal to noise ratio, which in turn enhanced the QoS at the point of reception. △ Less

Submitted 11 November, 2024; originally announced November 2024.

Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar

Authors: David Borts, Erich Liang, Tim Brödermann, Andrea Ramazzina, Stefanie Walz, Edoardo Palladin, Jipeng Sun, David Bruggemann, Christos Sakaridis, Luc Van Gool, Mario Bijelic, Felix Heide

Abstract: …exist, neural reconstruction methods for radar as a sensing modality have been largely unexplored. Operating at millimeter wavelengths, radar sensors are robust to scattering in fog and rain, and, as such, offer a complementary modality to active and passive optical sensing techniques. Moreover, existing radar sensors are highly cost-effective and deployed b… ▽ More Neural fields have been broadly investigated as scene representations for the reproduction and novel generation of diverse outdoor scenes, including those autonomous vehicles and robots must handle. While successful approaches for RGB and LiDAR data exist, neural reconstruction methods for radar as a sensing modality have been largely unexplored. Operating at millimeter wavelengths, radar sensors are robust to scattering in fog and rain, and, as such, offer a complementary modality to active and passive optical sensing techniques. Moreover, existing radar sensors are highly cost-effective and deployed broadly in robots and vehicles that operate outdoors. We introduce Radar Fields - a neural scene reconstruction method designed for active radar imagers. Our approach unites an explicit, physics-informed sensor model with an implicit neural geometry and reflectance model to directly synthesize raw radar measurements and extract scene occupancy. The proposed method does not rely on volume rendering. Instead, we learn fields in Fourier frequency space, supervised with raw radar data. We validate the effectiveness of the method across diverse outdoor scenarios, including urban scenes with dense vehicles and infrastructure, and in harsh weather scenarios, where mm-wavelength sensing is especially favorable. △ Less

Submitted 9 May, 2024; v1 submitted 7 May, 2024; originally announced May 2024.

Comments: 8 pages, 6 figures, to be published in SIGGRAPH 2024

A Review on Industrial Augmented Reality Systems for the Industry 4.0 Shipyard

Authors: Paula Fraga-Lamas, Tiago M Fernandez-Carames, Oscar Blanco-Novoa, Miguel Vilar-Montesinos

Abstract: …are compared. Finally, as a conclusion after reviewing all the aspects related to IAR for shipbuilding, it is proposed an IAR system architecture that combines Cloudlets and Fog Computing, which reduce latency response and accelerate rendering tasks while offloading compute intensive tasks from the Cloud. ▽ More Shipbuilding companies are upgrading their inner workings in order to create Shipyards 4.0, where the principles of Industry 4.0 are paving the way to further digitalized and optimized processes in an integrated network. Among the different Industry 4.0 technologies, this article focuses on Augmented Reality, whose application in the industrial field has led to the concept of Industrial Augmented Reality (IAR). This article first describes the basics of IAR and then carries out a thorough analysis of the latest IAR systems for industrial and shipbuilding applications. Then, in order to build a practical IAR system for shipyard workers, the main hardware and software solutions are compared. Finally, as a conclusion after reviewing all the aspects related to IAR for shipbuilding, it is proposed an IAR system architecture that combines Cloudlets and Fog Computing, which reduce latency response and accelerate rendering tasks while offloading compute intensive tasks from the Cloud. △ Less

Submitted 1 February, 2024; originally announced May 2024.

Comments: Accepted version of an IEEE Access journal article

Journal ref: P. Fraga-Lamas, T. M. Fernandez-Carames, O. Blanco-Novoa and M. A. Vilar-Montesinos, "A Review on Industrial Augmented Reality Systems for the Industry 4.0 Shipyard," in IEEE Access, vol. 6, pp. 13358-13375, 2018

Rendering Participating Media Using Path Graphs

Authors: Becky Hu, Xi Deng, Fujun Luan, Miloš Hašan, Steve Marschner

Abstract: Rendering volumetric scattering media, including clouds,… ▽ More Rendering volumetric scattering media, including clouds, fog, smoke, and other complex materials, is crucial for realism in computer graphics. Traditional path tracing, while unbiased, requires many long path samples to converge in scenes with scattering media, and a lot of work is wasted by paths that make a negligible contribution to the image. Methods to make better use of the information learned during path tracing range from photon mapping to radiance caching, but struggle to support the full range of heterogeneous scattering media. This paper introduces a new volumetric rendering algorithm that extends and adapts the previous \emph{path graph} surface rendering algorithm. Our method leverages the information collected through multiple-scattering transport paths to compute lower-noise estimates, increasing computational efficiency by reducing the required sample count. Our key contributions include an extended path graph for participating media and new aggregation and propagation operators for efficient path reuse in volumes. Compared to previous methods, our approach significantly boosts convergence in scenes with challenging volumetric light transport, including heterogeneous media with high scattering albedos and dense, forward-scattering translucent materials, under complex lighting conditions. △ Less

Submitted 18 April, 2024; originally announced April 2024.

Into the Fog: Evaluating Robustness of Multiple Object Tracking

Authors: Nadezda Kirillova, M. Jehanzeb Mirza, Horst Bischof, Horst Possegger

Abstract: …when trained and evaluated on current benchmarks. However, these benchmarks primarily consist of clear weather scenarios, overlooking adverse atmospheric conditions such as fog, haze, smoke and dust. As a result, the robustness of trackers against these challenging conditions remains underexplored. To address this gap, we introduce physics-based volumetric… ▽ More State-of-the-art Multiple Object Tracking (MOT) approaches have shown remarkable performance when trained and evaluated on current benchmarks. However, these benchmarks primarily consist of clear weather scenarios, overlooking adverse atmospheric conditions such as fog, haze, smoke and dust. As a result, the robustness of trackers against these challenging conditions remains underexplored. To address this gap, we introduce physics-based volumetric fog simulation method for arbitrary MOT datasets, utilizing frame-by-frame monocular depth estimation and a fog formation optical model. We enhance our simulation by rendering both homogeneous and heterogeneous fog and propose to use the dark channel prior method to estimate atmospheric light, showing promising results even in night and indoor scenes. We present the leading benchmark MOTChallenge (third release) augmented with fog (smoke for indoor scenes) of various intensities and conduct a comprehensive evaluation of MOT methods, revealing their limitations under fog and fog-like challenges. △ Less

Submitted 13 November, 2024; v1 submitted 12 April, 2024; originally announced April 2024.

Journal ref: BMVC 2024

SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving

Authors: Yiming Xie, Henglu Wei, Zhenyi Liu, Xiaoyu Wang, Xiangyang Ji

Abstract: To advance research in learning-based defogging algorithms, various synthetic fog datasets have been developed. However, existing datasets created using the Atmospheric Scattering Model (ASM) or real-time… ▽ More To advance research in learning-based defogging algorithms, various synthetic fog datasets have been developed. However, existing datasets created using the Atmospheric Scattering Model (ASM) or real-time rendering engines often struggle to produce photo-realistic foggy images that accurately mimic the actual imaging process. This limitation hinders the effective generalization of models from synthetic to real data. In this paper, we introduce an end-to-end simulation pipeline designed to generate photo-realistic foggy images. This pipeline comprehensively considers the entire physically-based foggy scene imaging process, closely aligning with real-world image capture methods. Based on this pipeline, we present a new synthetic fog dataset named SynFog, which features both sky light and active lighting conditions, as well as three levels of fog density. Experimental results demonstrate that models trained on SynFog exhibit superior performance in visual perception and detection accuracy compared to others when applied to real-world foggy images. △ Less

Submitted 25 March, 2024; originally announced March 2024.

Droplet morphology-based wettability tuning and design of fog harvesting mesh to minimize mesh-clogging

Authors: Arani Mukhopadhyay, Arkadeep Datta, Partha Sarathi Dutta, Amitava Datta, Ranjan Ganguly

Abstract: Fog harvesting relies on intercepting atmospheric or industrial… ▽ More Fog harvesting relies on intercepting atmospheric or industrial fog by placing a porous obstacle, e.g., a mesh and collecting the deposited water. In the face of global water scarcity, such fog harvesting has emerged as a viable alternative source of potable water. Typical fog harvesting meshes suffer from poor collection efficiency due to aerodynamic bypassing of the oncoming fog stream and poor collection of the deposited water from the mesh. One pestering challenge in this context is the frequent clogging up of mesh pores by the deposited fog water, which not only yields low drainage efficiency but also generates high aerodynamic resistance to the oncoming fog stream, thereby negatively impacting the fog collection efficiency. Minimizing the clogging is possible by rendering the mesh fiber superhydrophobic, but that entails other detrimental effects like premature dripping and flow-induced re-entrainment of water droplets into the fog stream from the mesh fiber. Herein, we improvise on the traditional interweaved metal mesh designs by defining critical parameters, viz., mesh pitch, shade coefficient, and fiber wettability, and deduce their optimal values from numerically and experimentally observed morphology of collected fog-water droplets under various operating scenarios. We extend our investigations over a varying range of mesh-wettability, including superhydrophilic and hydrophobic fibers, and go on to find optimal shade coefficients which would theoretically render clog-proof fog harvesting meshes. The aerodynamic, deposition, and overall collection efficiencies are characterized. Hydrophobic meshes with square pores, having fiber diameters smaller than the capillary length scale of water, and an optimal shade coefficient, are found to be the most effective design of such clog-proof meshes. △ Less

Submitted 3 April, 2024; v1 submitted 10 January, 2024; originally announced January 2024.

Comments: Arani and Arkadeep contributed equally. Corresponding author: Prof. Ranjan Ganguly (Email: ranjan.ganguly@jadavpuruniversity.in). All work carried out in the Advanced Materials Research and Applications (AMRA) Laboratory, India

Removing Adverse Volumetric Effects From Trained Neural Radiance Fields

Authors: Andreas L. Teigen, Mauhing Yip, Victor P. Hamran, Vegard Skui, Annette Stahl, Rudolf Mester

Abstract: …have there been any contributions that focus on the use of NeRF in foggy environments. We argue that the traditional NeRF models are able to replicate scenes filled with fog and propose a method to remove the… ▽ More While the use of neural radiance fields (NeRFs) in different challenging settings has been explored, only very recently have there been any contributions that focus on the use of NeRF in foggy environments. We argue that the traditional NeRF models are able to replicate scenes filled with fog and propose a method to remove the fog when synthesizing novel views. By calculating the global contrast of a scene, we can estimate a density threshold that, when applied, removes all visible fog. This makes it possible to use NeRF as a way of rendering clear views of objects of interest located in fog-filled environments. Additionally, to benchmark performance on such scenes, we introduce a new dataset that expands some of the original synthetic NeRF scenes through the addition of fog and natural environments. The code, dataset, and video results can be found on our project page: https://vegardskui.com/fognerf/ △ Less

Submitted 17 November, 2023; originally announced November 2023.

Comments: This work has been submitted to the IEEE for possible publication

Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services

Authors: Liekang Zeng, Xu Chen, Peng Huang, Ke Luo, Xiaoxi Zhang, Zhi Zhou

Abstract: …Neural Networks (GNNs) have gained growing interest in miscellaneous applications owing to their outstanding ability in extracting latent representation on graph structures. To render GNN-based service for IoT-driven smart applications, traditional model serving paradigms usually resort to the cloud by fully uploading geo-distributed input data to remote dat… ▽ More Graph Neural Networks (GNNs) have gained growing interest in miscellaneous applications owing to their outstanding ability in extracting latent representation on graph structures. To render GNN-based service for IoT-driven smart applications, traditional model serving paradigms usually resort to the cloud by fully uploading geo-distributed input data to remote datacenters. However, our empirical measurements reveal the significant communication overhead of such cloud-based serving and highlight the profound potential in applying the emerging fog computing. To maximize the architectural benefits brought by fog computing, in this paper, we present Fograph, a novel distributed real-time GNN inference framework that leverages diverse and dynamic resources of multiple fog nodes in proximity to IoT data sources. By introducing heterogeneity-aware execution planning and GNN-specific compression techniques, Fograph tailors its design to well accommodate the unique characteristics of GNN serving in fog environments. Prototype-based evaluation and case study demonstrate that Fograph significantly outperforms the state-of-the-art cloud serving and fog deployment by up to 5.39x execution speedup and 6.84x throughput improvement. △ Less

Submitted 4 July, 2023; originally announced July 2023.

Comments: Accepted by IEEE/ACM Transactions on Networking

Distracting Downpour: Adversarial Weather Attacks for Motion Estimation

Authors: Jenny Schmalfuss, Lukas Mehl, Andrés Bruhn

Abstract: …Hence, in this work, we present a novel attack on motion estimation that exploits adversarially optimized particles to mimic weather effects like snowflakes, rain streaks or fog clouds. At the core of our attack framework is a differentiable particle rendering system that integrates particles (i) consistently over mul… ▽ More Current adversarial attacks on motion estimation, or optical flow, optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, adverse weather conditions constitute a much more realistic threat scenario. Hence, in this work, we present a novel attack on motion estimation that exploits adversarially optimized particles to mimic weather effects like snowflakes, rain streaks or fog clouds. At the core of our attack framework is a differentiable particle rendering system that integrates particles (i) consistently over multiple time steps (ii) into the 3D space (iii) with a photo-realistic appearance. Through optimization, we obtain adversarial weather that significantly impacts the motion estimation. Surprisingly, methods that previously showed good robustness towards small per-pixel perturbations are particularly vulnerable to adversarial weather. At the same time, augmenting the training with non-optimized weather increases a method's robustness towards weather effects and improves generalizability at almost no additional cost. Our code will be available at https://github.com/cv-stuttgart/DistractingDownpour. △ Less

Submitted 27 July, 2023; v1 submitted 11 May, 2023; originally announced May 2023.

Comments: Acepted by ICCV 2023. This work is a direct extension of our extended abstract from arXiv:2210.11242

ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering

Authors: Andrea Ramazzina, Mario Bijelic, Stefanie Walz, Alessandro Sanvito, Dominik Scheuble, Felix Heide

Abstract: Vision in adverse weather conditions, whether it be snow, rain, or fog is challenging. In these scenarios, scattering and attenuation severly degrades image quality. Handling such inclement weather conditions, however, is essential to operate autonomous vehicles, drones and robotic applications where human performance is impeded the most. A large body of wor… ▽ More Vision in adverse weather conditions, whether it be snow, rain, or fog is challenging. In these scenarios, scattering and attenuation severly degrades image quality. Handling such inclement weather conditions, however, is essential to operate autonomous vehicles, drones and robotic applications where human performance is impeded the most. A large body of work explores removing weather-induced image degradations with dehazing methods. Most methods rely on single images as input and struggle to generalize from synthetic fully-supervised training approaches or to generate high fidelity results from unpaired real-world datasets. With data as bottleneck and most of today's training data relying on good weather conditions with inclement weather as outlier, we rely on an inverse rendering approach to reconstruct the scene content. We introduce ScatterNeRF, a neural rendering method which adequately renders foggy scenes and decomposes the fog-free background from the participating media-exploiting the multiple views from a short automotive sequence without the need for a large training data corpus. Instead, the rendering approach is optimized on the multi-view scene itself, which can be typically captured by an autonomous vehicle, robot or drone during operation. Specifically, we propose a disentangled representation for the scattering volume and the scene objects, and learn the scene reconstruction with physics-inspired losses. We validate our method by capturing multi-view In-the-Wild data and controlled captures in a large-scale fog chamber. △ Less

Submitted 3 May, 2023; originally announced May 2023.

Reliable Image Dehazing by NeRF

Authors: Zheyan Jin, Shiqi Chen, Huajun Feng, Zhihai Xu, Qi Li, Yueting Chen

Abstract: …dehazing model, and propose a new and reliable dehazing reconstruction and dehazing model based on the combination of optical scattering model and computer graphics lighting rendering model. Based on the new haze model and the images obtained by the cameras, we can reconstruct the three-dimensional space, accurately calculate the objects and haze in the spac… ▽ More We present an image dehazing algorithm with high quality, wide application, and no data training or prior needed. We analyze the defects of the original dehazing model, and propose a new and reliable dehazing reconstruction and dehazing model based on the combination of optical scattering model and computer graphics lighting rendering model. Based on the new haze model and the images obtained by the cameras, we can reconstruct the three-dimensional space, accurately calculate the objects and haze in the space, and use the transparency relationship of haze to perform accurate haze removal. To obtain a 3D simulation dataset we used the Unreal 5 computer graphics rendering engine. In order to obtain real shot data in different scenes, we used fog generators, array cameras, mobile phones, underwater cameras and drones to obtain haze data. We use formula derivation, simulation data set and real shot data set result experimental results to prove the feasibility of the new method. Compared with various other methods, we are far ahead in terms of calculation indicators (4 dB higher quality average scene), color remains more natural, and the algorithm is more robust in different scenarios and best in the subjective perception. △ Less

Submitted 16 March, 2023; originally announced March 2023.

Comments: 12pages, 8figures