arXiv Query: search_query=all:"real-time path tracing" OR all:"real-time global illumination" OR all:ReSTIR OR all:"radiance caching"&id_list=&start=0&max_results=30

Split Radiance Cascades: Real-Time Global Illumination via Sparse Radiance Probes

2026-07-22T17:13:18Z

Radiance probe methods are a popular and well-tested approach for approximating diffuse global illumination for real-time graphics, but they commonly suffer from a lack of detail due to the large spacing between probes. Radiance Cascade (RC) fixes this by increasing spatial resolution and reducing angular resolution for light and occlusion from closer objects, which allows it to provide details at all scales without noise or aliasing. However, leading implementations of RC either run in 2D or screenspace, due to the prohibitive costs of storing high-detail volumetric radiance information. In this work, we adapt Radiance Cascades for accurate real-time 3D diffuse global illumination using a sparse hashmap to store world-space probes. We introduce ray splitting, a method for calculating radiance intervals used in RC by tracing rays from visible surfaces and calculating their contribution to cascades based on their hit distance. We evaluate our algorithm, Split Radiance Cascades, on a variety of scenes, and demonstrate that it can provide high-quality indirect illumination in both single-frame and temporally accumulated contexts.

HoloPathTracer: Fast and Accurate Wave Path Tracing for Holography

2026-06-16T06:49:06Z

Holography offers unique advantages for delivering perceptual realism while preserving compact form factors in VR/AR. Its perceptual quality, however, hinges on encoding rich wavefronts of photorealistic scenes into interference patterns and then incoherently multiplexing the resulting wave fields for perception. Existing CGH paradigms decouple radiance estimation from wave propagation by pre-rendering radiance on discretized scene sectors. This separation between radiometric and wave-optical computation inherently limits the range of focus cues and visual effects that can be faithfully reproduced, including depth- and view-continuity, and physically based material behaviors such as glossy or mirror-like reflection and refraction. We present a physically accurate yet computationally efficient wave optics rendering framework leveraging path tracing to encode full 3D visual cues into phase holograms. Specifically, we employ a Monte Carlo method to solve both the rendering equation and the Rayleigh--Sommerfeld integral simultaneously. Our algorithm is fully compatible with modern graphics techniques and can generate multiple time-multiplexed random holograms with minimal additional time cost via Path Reuse. By employing a fast approximation with an ambient radiance cache, we realize an order of magnitude convergence speed improvement. The resulting coherent wave fields that inherently encode comprehensive visual effects are converted into phase-only holograms under complex-amplitude supervision. Through extensive simulations and experimental validations on a spatial light modulator-based display prototype, we demonstrate faithful holographic reconstructions of natural 3D cues and complex materials, including realistic defocus blur, view-dependent effects, as well as appearance highlights and reflections.

OctaOctree Neural Radiosity for Real-time Glossy Material Rendering

2026-06-07T06:25:23Z

Modeling high-frequency outgoing radiance distributions remains a fundamental challenge in global illumination, especially for glossy and specular materials. Existing neural-based radiance caching methods commonly rely on positional feature encodings or spatially organized caches, which makes it difficult to represent sharp directional radiance variations without increasing the model complexity or sampling cost. To address this challenge, we propose OctaOctree, an efficient spatial-angular radiance representation for global illumination. OctaOctree organizes outgoing radiance with an adaptive octree in 3D space, and associates each spatial node with an octahedral directional map. By coupling the spatial hierarchy with direction-dependent storage, our representation allocates fine spatial resolution to local illumination and visibility changes, while using coarser spatial levels with richer angular resolution to capture glossy and specular radiance distributions. This design embeds a reflectance-aware spatial-angular prior directly into the radiance representation, reducing the burden on neural networks or reconstruction modules to recover high-frequency view-dependent effects from positional features alone. As a result, OctaOctree provides a compact and expressive neural encoding for a wide range of indirect illumination effects, from diffuse interreflection to sharp glossy reflections. Experiments demonstrate that our method produces high-quality, direction-aware global illumination with single network query at primary intersections, achieving improved fidelity and real-time performance compared with baseline neural radiosity and radiance caching approaches.

Megakernel vs Wavefront GPU Path Tracing

2026-05-26T17:34:04Z

Over the last decade, advances in GPU hardware have been driven in large part by the demands of real-time graphics, culminating in dedicated hardware ray tracing cores (RT cores). These units accelerate ray scene intersection queries directly in hardware, making physically based ray tracing algorithms increasingly practical for interactive applications. This paper compares and analyzes the performance of two ray-based rendering algorithms: forward path tracing (PT) and wavefront path tracing (WPT). GPU-based PT computes the color of each pixel by having each thread trace a single path to completion, naturally leading to a megakernel approach - while WPT maintains state buffers between specialized kernel invocations to trace path stages simultaneously. We find that WPT affords a ~16% speedup over PT in our implementation. By analyzing traces from NVIDIA Nsight Graphics, we attributed this speedup to WPT's improved cache locality compared to PT. We also find that our implementation does not achieve maximum GPU throughput across any of its units, suggesting that communication and memory latency, as well as synchronization, are the limiting factors. Finally, we address potential algorithmic improvements and future work for real-time path tracing implementation for practical applications.

ToF ReSTIR: Time-of-Flight Rendering with Spatio-temporal Reservoir Resampling

2026-05-12T05:02:17Z

We present a novel spatio-temporal reuse framework for time-resolved light transport, enabling efficient Monte Carlo rendering of time-of-flight (ToF) phenomena such as time-gated imaging and transient light capture. Existing ToF rendering methods are computationally expensive, scale poorly to complex dynamic scenes, and are therefore unsuitable for applications with strict latency constraints. To address this limitation, we draw inspiration from ReSTIR, a reuse-based technique for steady-state real-time rendering, and adapt its core principles to interactive-rate ToF simulation. However, naively applying existing ReSTIR methods to ToF rendering leads to severe inefficiency, as reused paths frequently violate optical path-length constraints and thus contribute little or no signal. We overcome this challenge by introducing a path reuse formulation that explicitly enforces physically valid optical path lengths. The key idea is path-length-aware shift mapping, a geometric transformation based on Newton's method that adjusts reused light paths to satisfy temporal gating constraints, inspired by specular manifold exploration in steady-state caustics rendering. The resulting framework substantially improves the efficiency of ToF rendering across a wide range of scenarios, including complex scenes with glossy or specular materials and dynamic motion. Our method supports both time-gated and transient rendering at interactive frame rates, enabling simulation under practical latency constraints. We demonstrate the effectiveness of our approach through two downstream applications, including shape reconstruction and navigation.

Forget Superresolution, Sample Adaptively (when Path Tracing)

2026-02-09T13:39:20Z

Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. While super-resolution is widely used in production, it uniformly sacrifices spatial detail and cannot exploit variations in noise, reconstruction difficulty, and perceptual importance across the image. Adaptive sampling offers a compelling alternative, but existing end-to-end approaches rely on approximations that break down in sparse regimes. We introduce an end-to-end adaptive sampling and denoising pipeline explicitly designed for the sub-1-spp regime. Our method uses a stochastic formulation of sample placement that enables gradient estimation despite discrete sampling decisions, allowing stable training of a neural sampler at low sampling budgets. To better align optimization with human perception, we propose a tonemapping-aware training pipeline that integrates differentiable filmic operators and a state-of-the-art perceptual loss, preventing oversampling of regions with low visual impact. In addition, we introduce a gather-based pyramidal denoising filter and a learnable generalization of albedo demodulation tailored to sparse sampling. Our results show consistent improvements over uniform sparse sampling, with notably better reconstruction of perceptually critical details such as specular highlights and shadow boundaries, and demonstrate that adaptive sampling remains effective even at minimal budgets.

GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Camera

2025-11-28T03:24:12Z

Inverse rendering of indoor scenes remains challenging due to the ambiguity between reflectance and lighting, exacerbated by inter-reflections among multiple objects. While natural illumination-based methods struggle to resolve this ambiguity, co-located light-camera setups offer better disentanglement as lighting can be easily calibrated via Structure-from-Motion. However, such setups introduce additional complexities like strong inter-reflections, dynamic shadows, near-field lighting, and moving specular highlights, which existing approaches fail to handle. We present GLOW, a Global Illumination-aware Inverse Rendering framework designed to address these challenges. GLOW integrates a neural implicit surface representation with a neural radiance cache to approximate global illumination, jointly optimizing geometry and reflectance through carefully designed regularization and initialization. We then introduce a dynamic radiance cache that adapts to sharp lighting discontinuities from near-field motion, and a surface-angle-weighted radiometric loss to suppress specular artifacts common in flashlight captures. Experiments show that GLOW substantially outperforms prior methods in material reflectance estimation under both natural and co-located illumination.

GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splatting

2025-08-02T23:59:11Z

Real-time path tracing is rapidly becoming the standard for rendering in entertainment and professional applications. In scientific visualization, volume rendering plays a crucial role in helping researchers analyze and interpret complex 3D data. Recently, photorealistic rendering techniques have gained popularity in scientific visualization, yet they face significant challenges. One of the most prominent issues is slow rendering performance and high pixel variance caused by Monte Carlo integration. In this work, we introduce a novel radiance caching approach for path-traced volume rendering. Our method leverages advances in volumetric scene representation and adapts 3D Gaussian splatting to function as a multi-level, path-space radiance cache. This cache is designed to be trainable on the fly, dynamically adapting to changes in scene parameters such as lighting configurations and transfer functions. By incorporating our cache, we achieve less noisy, higher-quality images without increasing rendering costs. To evaluate our approach, we compare it against a baseline path tracer that supports uniform sampling and next-event estimation and the state-of-the-art for neural radiance caching. Through both quantitative and qualitative analyses, we demonstrate that our path-space radiance cache is a robust solution that is easy to integrate and significantly enhances the rendering quality of volumetric visualization applications while maintaining comparable computational efficiency.

GATE: Geometry-Aware Trained Encoding

2025-07-27T09:58:25Z

The encoding of input parameters is one of the fundamental building blocks of neural network algorithms. Its goal is to map the input data to a higher-dimensional space, typically supported by trained feature vectors. The mapping is crucial for the efficiency and approximation quality of neural networks. We propose a novel geometry-aware encoding called GATE that stores feature vectors on the surface of triangular meshes. Our encoding is suitable for neural rendering-related algorithms, for example, neural radiance caching. It also avoids limitations of previous hash-based encoding schemes, such as hash collisions, selection of resolution versus scene size, and divergent memory access. Our approach decouples feature vector density from geometry density using mesh colors, while allowing for finer control over neural network training and adaptive level-of-detail.

Neural Visibility Cache for Real-Time Light Sampling

2025-08-29T09:58:17Z

Direct illumination with many lights is an inherent component of physically-based rendering, remaining challenging, especially in real-time scenarios. We propose an online-trained neural cache that stores visibility between lights and 3D positions. We feed light visibility to weighted reservoir sampling (WRS) to sample a light source. The cache is implemented as a fully-fused multilayer perceptron (MLP) with multi-resolution hash-grid encoding, enabling online training and efficient inference on modern GPUs in real-time frame rates. The cache can be seamlessly integrated into existing rendering frameworks and can be used in combination with other real-time techniques such as spatiotemporal reservoir sampling (ReSTIR).

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

2025-06-06T02:20:49Z

3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages the color integration process of 3DGS to decrease the frequency of intensive rasterization computations. Coupled with these techniques, we propose an accelerator architecture, LuminCore, to further accelerate cache lookup and address the fundamental inefficiencies in Rasterization. We show that Lumina achieves 4.5x speedup and 5.3x energy reduction against a mobile Volta GPU, with a marginal quality loss (< 0.2 dB peak signal-to-noise ratio reduction) across synthetic and real-world datasets.

Neural Inverse Rendering from Propagating Light

2025-06-05T17:59:55Z

We present the first system for physically based, neural inverse rendering from multi-viewpoint videos of propagating light. Our approach relies on a time-resolved extension of neural radiance caching -- a technique that accelerates inverse rendering by storing infinite-bounce radiance arriving at any point from any direction. The resulting model accurately accounts for direct and indirect light transport effects and, when applied to captured measurements from a flash lidar system, enables state-of-the-art 3D reconstruction in the presence of strong indirect light. Further, we demonstrate view synthesis of propagating light, automatic decomposition of captured measurements into direct and indirect components, as well as novel capabilities such as multi-view time-resolved relighting of captured scenes.

Real-time Global Illumination for Dynamic 3D Gaussian Scenes

2026-04-29T10:39:38Z

We present a real-time global illumination approach along with a pipeline for dynamic 3D Gaussian models and meshes. Building on a formulated surface light transport model for 3D Gaussians, we address key performance challenges with a fast compound stochastic ray-tracing algorithm and an optimized 3D Gaussian rasterizer. Our pipeline integrates multiple real-time techniques to accelerate performance and achieve high-quality lighting effects. Our approach enables real-time rendering of dynamic scenes with interactively editable materials and dynamic lighting of diverse multi-lights settings, capturing mutual multi-bounce light transport (indirect illumination) between 3D Gaussians and mesh. Additionally, we present a real-time renderer with an interactive user interface, validating our approach and demonstrating its practicality and high efficiency with over 40 fps in scenes including both 3D Gaussians and mesh. Furthermore, our work highlights the potential of 3D Gaussians in real-time applications with dynamic lighting, offering insights into performance and optimization.

Neural Two-Level Monte Carlo Real-Time Rendering

2024-12-05T22:06:23Z

We introduce an efficient Two-Level Monte Carlo (subset of Multi-Level Monte Carlo, MLMC) estimator for real-time rendering of scenes with global illumination. Using MLMC we split the shading integral into two parts: the radiance cache integral and the residual error integral that compensates for the bias of the first one. For the first part, we developed the Neural Incident Radiance Cache (NIRC) leveraging the power of fully-fused tiny neural networks as a building block, which is trained on the fly. The cache is designed to provide a fast and reasonable approximation of the incident radiance: an evaluation takes 2-25x less compute time than a path tracing sample. This enables us to estimate the radiance cache integral with a high number of samples and by this achieve faster convergence. For the residual error integral, we compute the difference between the NIRC predictions and the unbiased path tracing simulation. Our method makes no assumptions about the geometry, materials, or lighting of a scene and has only few intuitive hyper-parameters. We provide a comprehensive comparative analysis in different experimental scenarios. Since the algorithm is trained in an on-line fashion, it demonstrates significant noise level reduction even for dynamic scenes and can easily be combined with other importance sampling schemes and noise reduction techniques.

Fast and Accurate Neural Rendering Using Semi-Gradients

2024-10-14T04:30:38Z

We propose a simple yet effective neural network-based framework for global illumination rendering. Recently, rendering techniques that learn neural radiance caches by minimizing the difference (i.e., residual) between the left and right sides of the rendering equation have been suggested. Due to their ease of implementation and the advantage of excluding path integral calculations, these techniques have been applied to various fields, such as free-viewpoint rendering, differentiable rendering, and real-time rendering. However, issues of slow training and occasionally darkened renders have been noted. We identify the cause of these issues as the bias and high variance present in the gradient estimates of the existing residual-based objective function. To address this, we introduce a new objective function that maintains the same global optimum as before but allows for unbiased and low-variance gradient estimates, enabling faster and more accurate training of neural networks. In conclusion, this method is simply implemented by ignoring the partial derivatives of the right-hand side, and theoretical and experimental analyses demonstrate the effectiveness of the proposed loss.

Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering

2024-09-09T17:59:57Z

State-of-the-art techniques for 3D reconstruction are largely based on volumetric scene representations, which require sampling multiple points to compute the color arriving along a ray. Using these representations for more general inverse rendering -- reconstructing geometry, materials, and lighting from observed images -- is challenging because recursively path-tracing such volumetric representations is expensive. Recent works alleviate this issue through the use of radiance caches: data structures that store the steady-state, infinite-bounce radiance arriving at any point from any direction. However, these solutions rely on approximations that introduce bias into the renderings and, more importantly, into the gradients used for optimization. We present a method that avoids these approximations while remaining computationally efficient. In particular, we leverage two techniques to reduce variance for unbiased estimators of the rendering equation: (1) an occlusion-aware importance sampler for incoming illumination and (2) a fast cache architecture that can be used as a control variate for the radiance from a high-quality, but more expensive, volumetric cache. We show that by removing these biases our approach improves the generality of radiance cache based inverse rendering, as well as increasing quality in the presence of challenging light transport effects such as specular reflections.

Neural Scene Baking for Permutation Invariant Transparency Rendering with Real-time Global Illumination

2024-05-29T12:56:18Z

Neural rendering provides a fundamentally new way to render photorealistic images. Similar to traditional light-baking methods, neural rendering utilizes neural networks to bake representations of scenes, materials, and lights into latent vectors learned from path-tracing ground truths. However, existing neural rendering algorithms typically use G-buffers to provide position, normal, and texture information of scenes, which are prone to occlusion by transparent surfaces, leading to distortions and loss of detail in the rendered images. To address this limitation, we propose a novel neural rendering pipeline that accurately renders the scene behind transparent surfaces with global illumination and variable scenes. Our method separates the G-buffers of opaque and transparent objects, retaining G-buffer information behind transparent objects. Additionally, to render the transparent objects with permutation invariance, we designed a new permutation-invariant neural blending function. We integrate our algorithm into an efficient custom renderer to achieve real-time performance. Our results show that our method is capable of rendering photorealistic images with variable scenes and viewpoints, accurately capturing complex transparent structures along with global illumination. Our renderer can achieve real-time performance ($256\times 256$ at 63 FPS and $512\times 512$ at 32 FPS) on scenes with multiple variable transparent objects.

Rendering Participating Media Using Path Graphs

2024-04-18T04:47:27Z

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.

GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering

2026-04-13T05:59:38Z

In this paper, we present GaNI, a Global and Near-field Illumination-aware neural inverse rendering technique that can reconstruct geometry, albedo, and roughness parameters from images of a scene captured with co-located light and camera. Existing inverse rendering techniques with co-located light-camera focus on single objects only, without modeling global illumination and near-field lighting more prominent in scenes with multiple objects. We introduce a system that solves this problem in two stages; we first reconstruct the geometry powered by neural volumetric rendering NeuS, followed by inverse neural radiosity that uses the previously predicted geometry to estimate albedo and roughness. However, such a naive combination fails and we propose multiple technical contributions that enable this two-stage approach. We observe that NeuS fails to handle near-field illumination and strong specular reflections from the flashlight in a scene. We propose to implicitly model the effects of near-field illumination and introduce a surface angle loss function to handle specular reflections. Similarly, we observe that invNeRad assumes constant illumination throughout the capture and cannot handle moving flashlights during capture. We propose a light position-aware radiance cache network and additional smoothness priors on roughness to reconstruct reflectance. Experimental evaluation on synthetic and real data shows that our method outperforms the existing co-located light-camera-based inverse rendering techniques. Our approach produces significantly better reflectance and slightly better geometry than capture strategies that do not require a dark room.

GI-1.0: A Fast and Scalable Two-level Radiance Caching Scheme for Real-time Global Illumination

2023-10-30T17:14:49Z

Real-time global illumination is key to enabling more dynamic and physically realistic worlds in performance-critical applications such as games or any other applications with real-time constraints.Hardware-accelerated ray tracing in modern GPUs allows arbitrary intersection queries against the geometry, making it possible to evaluate indirect lighting entirely at runtime. However, only a small number of rays can be traced at each pixel to maintain high framerates at ever-increasing image resolutions. Existing solutions, such as probe-based techniques, approximate the irradiance signal at the cost of a few rays per frame but suffer from a lack of details and slow response times to changes in lighting. On the other hand, reservoir-based resampling techniques capture much more details but typically suffer from poorer performance and increased amounts of noise, making them impractical for the current generation of hardware and gaming consoles. To find a balance that achieves high lighting fidelity while maintaining a low runtime cost, we propose a solution that dynamically estimates global illumination without needing any content preprocessing, thus enabling easy integration into existing real-time rendering pipelines.

RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing

2023-10-05T12:39:27Z

Monte-Carlo path tracing is a powerful technique for realistic image synthesis but suffers from high levels of noise at low sample counts, limiting its use in real-time applications. To address this, we propose a framework with end-to-end training of a sampling importance network, a latent space encoder network, and a denoiser network. Our approach uses reinforcement learning to optimize the sampling importance network, thus avoiding explicit numerically approximated gradients. Our method does not aggregate the sampled values per pixel by averaging but keeps all sampled values which are then fed into the latent space encoder. The encoder replaces handcrafted spatiotemporal heuristics by learned representations in a latent space. Finally, a neural denoiser is trained to refine the output image. Our approach increases visual quality on several challenging datasets and reduces rendering times for equal quality by a factor of 1.6x compared to the previous state-of-the-art, making it a promising solution for real-time applications.

Towards Neural Path Tracing in SRAM

2023-05-31T17:38:06Z

We present an experimental neural path tracer designed to exploit the large on-chip memory of Graphcore intelligence-processing-units (IPUs). This open source renderer demonstrates how to map path tracing to the novel software and hardware architecture and is a useful tool for analysing in-cache neural-rendering scenarios. Such scenarios will be increasingly important if rasterisation is replaced by combinations of ray/path tracing, neural-radiance caching, and AI denoising/up-scaling, for which small neural networks are already routinely employed. A detailed description of the implementation also serves as a self-contained resource for more general software design on IPU.

Joint Optimization of Triangle Mesh, Material, and Light from Neural Fields with Neural Radiance Cache

2025-06-06T06:35:52Z

Traditional inverse rendering techniques are based on textured meshes, which naturally adapts to modern graphics pipelines, but costly differentiable multi-bounce Monte Carlo (MC) ray tracing poses challenges for modeling global illumination. Recently, neural fields has demonstrated impressive reconstruction quality but falls short in modeling indirect illumination. In this paper, we introduce a simple yet efficient inverse rendering framework that combines the strengths of both methods. Specifically, given pre-trained neural field representing the scene, we can obtain an initial estimate of the signed distance field (SDF) and create a Neural Radiance Cache (NRC), an enhancement over the traditional radiance cache used in real-time rendering. By using the former to initialize differentiable marching tetrahedrons (DMTet) and the latter to model indirect illumination, we can compute the global illumination via single-bounce differentiable MC ray tracing and jointly optimize the geometry, material, and light through back propagation. Experiments demonstrate that, compared to previous methods, our approach effectively prevents indirect illumination effects from being baked into materials, thus obtaining the high-quality reconstruction of triangle mesh, Physically-Based (PBR) materials, and High Dynamic Range (HDR) light probe.

Photon Field Networks for Dynamic Real-Time Volumetric Global Illumination

2023-04-14T18:17:34Z

Volume data is commonly found in many scientific disciplines, like medicine, physics, and biology. Experts rely on robust scientific visualization techniques to extract valuable insights from the data. Recent years have shown path tracing to be the preferred approach for volumetric rendering, given its high levels of realism. However, real-time volumetric path tracing often suffers from stochastic noise and long convergence times, limiting interactive exploration. In this paper, we present a novel method to enable real-time global illumination for volume data visualization. We develop Photon Field Networks -- a phase-function-aware, multi-light neural representation of indirect volumetric global illumination. The fields are trained on multi-phase photon caches that we compute a priori. Training can be done within seconds, after which the fields can be used in various rendering tasks. To showcase their potential, we develop a custom neural path tracer, with which our photon fields achieve interactive framerates even on large datasets. We conduct in-depth evaluations of the method's performance, including visual quality, stochastic noise, inference and rendering speeds, and accuracy regarding illumination and phase function awareness. Results are compared to ray marching, path tracing and photon mapping. Our findings show that Photon Field Networks can faithfully represent indirect global illumination across the phase spectrum while exhibiting less stochastic noise and rendering at a significantly faster rate than traditional methods.

Decorrelating ReSTIR Samplers via MCMC Mutations

2022-10-31T22:15:16Z

Monte Carlo rendering algorithms often utilize correlations between pixels to improve efficiency and enhance image quality. For real-time applications in particular, repeated reservoir resampling offers a powerful framework to reuse samples both spatially in an image and temporally across multiple frames. While such techniques achieve equal-error up to 100 times faster for real-time direct lighting and global illumination, they are still far from optimal. For instance, unchecked spatiotemporal resampling often introduces noticeable correlation artifacts, while reservoirs holding more than one sample suffer from impoverishment in the form of duplicate samples. We demonstrate how interleaving Markov Chain Monte Carlo (MCMC) mutations with reservoir resampling helps alleviate these issues, especially in scenes with glossy materials and difficult-to-sample lighting. Moreover, our approach does not introduce any bias, and in practice we find considerable improvement in image quality with just a single mutation per reservoir sample in each frame.

Real-Time Path-Guiding Based on Parametric Mixture Models

2021-12-17T19:27:43Z

Path-Guiding algorithms for sampling scattering directions can drastically decrease the variance of Monte Carlo estimators of Light Transport Equation, but their usage was limited to offline rendering because of memory and computational limitations. We introduce a new robust screen-space technique that is based on online learning of parametric mixture models for guiding the real-time path-tracing algorithm. It requires storing of 8 parameters for every pixel, achieves a reduction of FLIP metric up to 4 times with 1 spp rendering. Also, it consumes less than 1.5ms on RTX 2070 for 1080p and reduces path-tracing timings by generating more coherent rays by about 5% on average. Moreover, it leads to significant bias reduction and a lower level of flickering of SVGF output.

Real Time Cluster Path Tracing

2021-10-21T20:23:38Z

Photorealistic rendering effects are common in films, but most real time graphics today still rely on scan-line based multi-pass rendering to deliver rich visual experiences. While there have been prior works in distributed path tracing for static scene and objects under rigid motion, real time path tracing of deforming characters has to support per-frame dynamic BVH changes. We present the architecture and implementation of the first real-time production quality cluster path tracing renderer that supports film quality animation and deformation. We build our cluster path tracing system using the open source Blender and its GPU accelerated production quality renderer Cycles. Our system's rendering performance and quality scales linearly with the number of RTX cluster nodes used. It is able to generate and deliver path traced images with global illumination effects to remote light-weight client systems at 15-30 frames per second for a variety of Blender scenes including animated digital human characters with skin deformation and virtual objects.

Real-time Neural Radiance Caching for Path Tracing

2021-06-25T08:09:48Z

We present a real-time neural radiance caching method for path-traced global illumination. Our system is designed to handle fully dynamic scenes, and makes no assumptions about the lighting, geometry, and materials. The data-driven nature of our approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation, i.e. we opt for training the radiance cache while rendering. We employ self-training to provide low-noise training targets and simulate infinite-bounce transport by merely iterating few-bounce training updates. The updates and cache queries incur a mild overhead -- about 2.6ms on full HD resolution -- thanks to a streaming implementation of the neural network that fully exploits modern hardware. We demonstrate significant noise reduction at the cost of little induced bias, and report state-of-the-art, real-time performance on a number of challenging scenarios.

Real-Time Global Illumination Using OpenGL And Voxel Cone Tracing

2021-04-01T16:49:59Z

Building systems capable of replicating global illumination models with interactive frame-rates has long been one of the toughest conundrums facing computer graphics researchers. Voxel Cone Tracing, as proposed by Cyril Crassin et al. in 2011, makes use of mipmapped 3D textures containing a voxelized representation of an environments direct light component to trace diffuse, specular and occlusion cones in linear time to extrapolate a surface fragments indirect light emitted towards a given photo-receptor. Seemingly providing a well-disposed balance between performance and physical fidelity, this thesis examines the algorithms theoretical side on the basis of the rendering equation as well as its practical side in the context of a self-implemented, OpenGL-based variant. Whether if it can compete with long standing alternatives such as radiosity and raytracing will be determined in the subsequent evaluation.

Deep Radiance Caching: Convolutional Autoencoders Deeper in Ray Tracing

2020-07-30T17:32:00Z

Rendering realistic images with global illumination is a computationally demanding task and often requires dedicated hardware for feasible runtime. Recent research uses Deep Neural Networks to predict indirect lighting on image level, but such methods are commonly limited to diffuse materials and require training on each scene.We present Deep Radiance Caching (DRC), an efficient variant of Radiance Caching utilizing Convolutional Autoencoders for rendering global illumination. DRC employs a denoising neural network with Radiance Caching to support a wide range of material types, without the requirement of offline pre-computation or training for each scene.This offers high performance CPU rendering for maximum accessibility. Our method has been evaluated on interior scenes, and is able to produce high-quality images within 180 seconds on a single CPU.