# daniilidis-group/neural_renderer

A PyTorch port of the Neural 3D Mesh Renderer

Repository: https://github.com/daniilidis-group/neural_renderer
Canonical: https://ross.abutalabs.com/products/neural_renderer
Language: Python
License: NOASSERTION
License Family: other
Last push: 2022-03-17T10:15:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3001, "days_push": 1630, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1167, forks 254 (observed 2026-08-28T04:03:50.716043+00:00)

## What it is
A PyTorch port of the Neural 3D Mesh Renderer (CVPR 2018), providing differentiable rasterization of 3D meshes. It supports rendering from multiple viewpoints and gradient-based optimization of vertices, textures, and camera parameters.

## Use cases
- render 3d meshes in pytorch with gradients
- optimize mesh vertices to match a silhouette
- optimize textures from a reference image
- estimate camera pose via gradient descent
- differentiable rendering for deep learning
- port chainer neural renderer to pytorch

## When to choose
- you need differentiable mesh rendering in PyTorch
- you want to reproduce the Neural 3D Mesh Renderer paper
- you need to optimize geometry, texture, or camera parameters end-to-end

## When to avoid
- you need a modern actively maintained renderer
- you require recent PyTorch versions without patching
- you need production 3D rendering rather than research use

## Facets
- artifact type: library
- maturity: maintenance
- function: graphics, machine-learning, image-processing
- domain: computer-vision, graphics, deep-learning
- platform: python
- tags: pytorch, 3d-rendering, differentiable-rendering, mesh-renderer, cvpr-2018, gpu

## Member repositories
- daniilidis-group/neural_renderer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:50.716043+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:28:50.976133+00:00, confidence not recorded.
  - readme: https://github.com/daniilidis-group/neural_renderer (fetched 2026-08-28T04:03:50.716043+00:00, sha 41d8decbf0a3)
- Data as of 2026-08-30T08:39:29.467469+00:00.