hiroharu-kato/neural_renderer

Health v2 · maintenance only

Adoption not part of the score

1164 stars · 157 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A differentiable 3D mesh renderer implemented in Chainer, accompanying the CVPR 2018 paper 'Neural 3D Mesh Renderer'. It enables gradient-based optimization over 3D mesh vertices, textures, and camera parameters through the rendering process.

Use cases

• render 3d meshes with gradients for deep learning
• optimize 3d mesh vertices from images
• optimize textures via differentiable rendering
• estimate camera pose by gradient descent
• single-image 3d mesh reconstruction research

When to choose

• doing research on differentiable rendering or 3D reconstruction from images
• you need gradients flowing through a rasterization pipeline in Chainer
• reproducing CVPR 2018 neural rendering baselines

When to avoid

• you work in PyTorch - use the community re-implementations instead
• you need a production-grade or actively maintained renderer
• you need full-featured rasterization like ray tracing or PBR shading

Facets

library · maturity maintenance

graphics machine-learning simulation computer-vision graphics deep-learning python differentiable-rendering 3d-mesh chainer cvpr-2018 computer-graphics gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hiroharu-kato/neural_renderer")