autonomousvision/mip-splatting

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1466 stars · 121 forks observed · 2026-08-28

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

Mip-Splatting is a research implementation of alias-free 3D Gaussian Splatting, introducing a 3D smoothing filter and 2D Mip filter to eliminate artifacts in novel view synthesis. It is the CVPR 2024 Best Student Paper codebase built on PyTorch with custom CUDA rasterization submodules.

Use cases

• reconstruct 3D scenes from images with gaussian splatting
• render novel views without aliasing artifacts
• train on single-scale images and test at multiple scales
• evaluate on NeRF synthetic and Mip-NeRF 360 datasets
• compare 3DGS variants for research

When to choose

• you need alias-free 3D Gaussian Splatting renderings across zoom levels
• you are doing research on novel view synthesis or NeRF alternatives
• you have a CUDA GPU and want state-of-the-art 3DGS quality

When to avoid

• you need a production 3D viewer or end-user application
• you lack a CUDA-capable GPU
• you want a maintained product rather than research code

Facets

library · maturity active

machine-learning computer-vision graphics image-processing computer-vision graphics deep-learning python 3d-gaussian-splatting novel-view-synthesis anti-aliasing nerf cvpr-2024 research-code cuda-rasterization linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="autonomousvision/mip-splatting")