# trianglesplatting/triangle-splatting

Repository: https://github.com/trianglesplatting/triangle-splatting
Canonical: https://ross.abutalabs.com/products/triangle-splatting
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-11-24T13:29:11+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 35, longevity 33
- inputs: {"age_days": 465, "days_push": 282, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1191, forks 95 (observed 2026-08-28T04:03:56.198503+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: graphics, machine-learning, simulation
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python
- tags: neural-rendering, radiance-fields, 3d-reconstruction, gaussian-splatting, differentiable-rendering, cuda-kernels, novel-view-synthesis, research-code, gpu, linux

## Member repositories
- trianglesplatting/triangle-splatting (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.198503+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 2026-08-30T06:22:59.062523+00:00, confidence not recorded.
  - readme: https://github.com/trianglesplatting/triangle-splatting (fetched 2026-08-28T04:03:56.198503+00:00, sha e4567174ff08)
- Data as of 2026-08-30T08:39:29.467469+00:00.