trianglesplatting/triangle-splatting

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1191 stars · 95 forks observed · 2026-08-28

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

Official implementation of 'Triangle Splatting for Real-Time Radiance Field Rendering' (3DV 2026), which uses 3D triangles as rendering primitives for radiance field rendering. It provides training, rendering, evaluation, and video generation scripts built on custom CUDA kernels.

Use cases

• train a radiance field model on captured scenes
• render novel views of a 3D scene in real time
• reproduce results from the Triangle Splatting paper on MipNeRF360
• generate fly-through videos from trained 3D scene models
• experiment with mesh-aware differentiable rendering primitives

When to choose

• you need real-time radiance field rendering with mesh-compatible triangle primitives
• you want to bridge neural rendering with traditional GPU graphics pipelines
• you are researching differentiable rendering or novel view synthesis

When to avoid

• you need a production-ready end-user 3D viewer or editor
• you lack a CUDA-capable GPU or want CPU-only rendering
• you need a mature, stable library with long-term API guarantees

Facets

library · maturity active

graphics machine-learning simulation computer-vision graphics machine-learning deep-learning python neural-rendering radiance-fields 3d-reconstruction gaussian-splatting differentiable-rendering cuda-kernels novel-view-synthesis research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="trianglesplatting/triangle-splatting")