#4040th of 89 in Image and videoFor image, video and design, 3d

opensplat

C++ trainer that turns COLMAP or OpenSfM camera poses into 3D gaussian splats

Stars
2.3k
License
AGPL-3.0
Last commit
Oct 2026
Last release
Sep 2026
Language
C++
Stars, last 29 weeks+326
25 Apr 2026: 1,938 stars2 May 2026: 1,953 stars9 May 2026: 1,967 stars16 May 2026: 1,984 stars23 May 2026: 1,995 stars30 May 2026: 2,006 stars6 Jun 2026: 2,028 stars13 Jun 2026: 2,040 stars20 Jun 2026: 2,050 stars27 Jun 2026: 2,063 stars4 Jul 2026: 2,076 stars11 Jul 2026: 2,084 stars18 Jul 2026: 2,094 stars25 Jul 2026: 2,105 stars1 Aug 2026: 2,114 stars8 Aug 2026: 2,125 stars15 Aug 2026: 2,139 stars22 Aug 2026: 2,154 stars29 Aug 2026: 2,163 stars5 Sept 2026: 2,175 stars12 Sept 2026: 2,179 stars19 Sept 2026: 2,188 stars26 Sept 2026: 2,197 stars3 Oct 2026: 2,207 stars10 Oct 2026: 2,221 stars17 Oct 2026: 2,231 stars24 Oct 2026: 2,239 stars31 Oct 2026: 2,248 stars7 Nov 2026: 2,259 stars14 Nov 2026: 2,264 stars

1,938 on 25 Apr 20262,264 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

OpenSplat is a command-line C++ implementation of 3D gaussian splatting. It reads camera poses and sparse points from ODX, OpenSfM, COLMAP, OpenMVG or nerfstudio projects and writes a scene as .ply, .splat, .spz or .rad. It trains on NVIDIA (CUDA), AMD (ROCm/HIP) and Apple (Metal) GPUs, or on CPU at roughly 100x slower.

Who it is for: Photogrammetry and 3D capture users training gaussian splats from SfM output

Strengths

  • Runs on CUDA, ROCm/HIP, Metal and plain CPU from one codebase
  • Reads ODX, OpenSfM, COLMAP, OpenMVG and nerfstudio projects directly
  • Supports image masks, resuming from a .ply and compressed .splat output
  • Documents GPU memory use: about 2 GB per million gaussians

Weaknesses

  • Requires sparse points in the input; random initialization is not supported
  • Source build needs OpenCV and a matching libtorch, which takes manual setup
  • Pre-built Windows binary is sold; free route is building from source
  • AGPL-3.0 license constrains use in closed-source products

What it needs

  • GPU optional
  • Docker
  • Needs libtorch, OpenCV, CUDA, ROCm, Xcode Metal toolchain, CMake
  • Models: COLMAP, OpenSfM, ODX, OpenMVG, nerfstudio

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Also in Image and video

See all 89
Also in Image and video
RankProjectScore
1frigateLocal NVR with realtime object detection for IP cameras37.6k starsMIT93 out of 100
2MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles144.3k starsMIT88 out of 100
3toonflow-appInfinite-canvas tool for AI short drama and comic video production22.1k starsMIT88 out of 100
#4InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows29.1k starsApache-2.087 out of 100
#5ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows147.4k starsGPL-3.085 out of 100