Nishi Human Program
→ BEYOND-METAHUMAN PROGRAM (live, updated each build round): /world/metahuman — the capability ruler, the honest distance to MetaHuman, the procedural face and skull built inside-out one measured unit at a time, with every rejected attempt published beside the shipped one.
Where we are, measured — and where we go, in the order the measurements demand. Every number here came from our own sovereign ruler; every failure is listed beside every win.
1. Where we are — measured, not asserted
The generator emits a human body from an anthropometric canon: 16 parts, ~341k triangles, three nested anatomical layers (bone core → muscle envelope → skin), digits produced by a parameterised rule, and the canon read from data rather than typed into code. It is measured against a real cadaver reference by nx_bodybench, which now runs five independent judges.
| Judge | What it sees | Score |
|---|---|---|
| front silhouette | outline, face-on | 823 |
| side silhouette | depth profile | 813 |
| normal field (shape) | surface orientation agreement | 923 |
| detail (front + back) | surface busyness vs the reference | 380 |
| three-quarter detail | lateral surface: flank, lats, arm/torso join | 255 |
| head region | the face alone | 227 |
Honest headline = the minimum = 255. Against a photograph rather than a cadaver, perceptual quality is roughly 175 — clay. The face is measurably our worst region.
2. What we learned — the laws that constrain the plan
3. Where we go
Phase 1 — Instruments (unblocks everything else)
nx_landmark— anatomical correspondence points (acromion, iliac crest, trochanter, patella, jaw apex, brow ridge, pupillary distance). Unblocks three sessions of measured-transfer results currently banked as failures.nx_campose— solve camera focal length and distance, replacing height-normalised framing so measurement is not warped by projection.- Head oracle — the face currently has no reference at all. GNM is Apache-2.0; verify the data licence separately from the repository licence.
- Two-ruler split — anatomical realism against the cadaver, aesthetic against ratio targets. Stylised proportions should score worse on realism; without the split every style win reads as a regression.
Phase 2 — Form and identity
- Correlated manifold sampler — human variation is correlated and low-dimensional, so independent sliders produce implausible people. Source the structure from measured populations, never from a generative prior.
- Aesthetic scorer — canonical ratios, symmetry and feature harmony as an explicit measured permil, so beauty becomes improvable and red-teamable rather than hand-tuned.
- True facial geometry — a brow, orbit and nose are shapes, not a radius nudged by nine percent. Scored on the head judge and the head oracle.
Phase 3 — Surface and light
- Anatomically shaped relief bases, tuned against the three-quarter and region judges rather than a body average.
- Screen-space occlusion, soft area shadows, depth of field — deferred deliberately until geometry gives light something to reveal.
Phase 4 — Population
- Village generator: demographic structure, shared latents for family resemblance, generate-and-score so every inhabitant is plausible and distinct.
- Presets as points on the aesthetic ruler, never as edits to the realism baseline. Post-generation sliders are a later fine-control layer, not part of the generator.
Phase 5 — Past MetaHuman
Not by out-polishing Epic's artists. MetaHuman is a closed asset ecosystem with a DNA file binding morphs to anatomy. Our axis is the one nobody else has: a body correct from the inside out — the nested bone, muscle and skin stack where the outer form emerges from the layers beneath, extended with real muscles, a vascular tree visible through translucent skin, and organs. Infinigen's creatures are single-surface; SMPL is a single skin shell; MetaHuman is a shell with a rig. None of them can show what is underneath, because there is nothing underneath.
4. Posture toward outside work
Third-party systems are oracles and capability bars, never the product — the same posture that has served us with CUDA. Take the mathematics, which is published and free to learn from; take no assets, no weights, no runtime. A generated human that comes out of someone else's checkpoint is neither ours nor reusable, which is the whole point of building it.
Standing boundary: photographic references are a quality bar. We build look classes parametrically; we do not replicate the likeness of a named living person, which needs their consent.