CUDA accelerated rasterization of gaussian splatting

★ 5,902⑂ 1,013👁 56⑃ 562● 536▤ 24
PythonApache-2.0Created 2023-08-25docs.gsplat.studio/
More from this author
Download: v1.5.3v1.5.3 ↓1.5.32025-07-04
+4
Daily
5,902
stars
1,013
forks
56
watchers
562
prs
536
issues
24
releases

README

gsplat




http://www.gsplat.studio/

gsplat is an open-source library for CUDA accelerated rasterization of gaussians with python bindings. It is inspired by the SIGGRAPH paper 3D Gaussian Splatting for Real-Time Rendering of Radiance Fields, but we’ve made gsplat even faster, more memory efficient, and with a growing list of new features! 


  


 News

 v1.6.0

Changes on main since the v1.5.3 tag (not yet on PyPI).

- [Aug 2026] Spherical-harmonics updates -- split diffuse and view-dependent operators, fused view-direction computation, and optimized backward kernels.
- [Jul 2026] Sparse 3DGS rasterization -- active-tile rendering with forward/backward support and sparse Gaussian ID, count, and top-contributor queries.
- [Jul 2026] Multi-GPU dense 3DGS -- distributed support for the dense rendering path.
- [Jul 2026] PPISP across densification strategies -- post-processing now works with both the default and MCMC strategies.
- [Jul 2026] Additional performance and code improvements:
  - Faster 3DGS and 3DGUT kernels -- optimized dense rasterization, spherical-harmonics feature assembly, and projection across sensor models.
  - Orthographic-camera support for 3DGUT.
  - Fused SE(3) operations for pose composition and trajectory interpolation.
  - More configurable MCMC operations for perturbation and relocation.
  - PyTorch 2.7+ is now required, with improved CUDA 12.8 and 13.2 build compatibility.
- [Jun 2026] G-SHARP -- dynamic surgical-scene reconstruction for Gaussian splatting.
- [Jun 2026] New camera & sensor support in the sensors library: pinhole, FTheta, fisheye, and LiDAR models.
- [Jun 2026] Faster rasterization -- a series of performance improvements across the 3DGS and 3DGUT rasterization paths. Noticing roughly 30% improvement on the 3DGUT MCMC path on an NVIDIA A100.
- [Jun 2026] Gaussian ID rasterization -- a new op to rasterize Gaussian IDs, counts, and top contributors per pixel.
- [Jun 2026] Various performance and code improvements:
  - Spherical-harmonics improvements -- support for arbitrary channel counts and fp16.
  - Profiling and tracing tools for diagnosing performance.
  - Robustness and stability fixes across the library.
  - Stronger test coverage, plus ahead-of-time (AOT) build/test CI.
  - CUDA 13 and NumPy 2 support.
  - Simplified package layout -- everything now lives under the gsplat namespace.
- [May 2026] Inference Rendering (HiGS) -- An experimental inference-only rendering path based on HiGS (Hierarchically Tiled Gaussian Splatting) is now available under the experimental package. The inference path uses macro-tile fused rasterization with fp16 scene packing for low-latency rendering of pre-trained Gaussian scenes. For more details, see the Inference Rendering section and the HiGS project page.
- [May 2026] Native CUDA MCMC perturb (inject_noise) speeds up the noise-injection step used in MCMC-style Gaussian optimization.
- [Apr 2026] AccuTile adds a conservative ellipse-based tile–Gaussian intersection t

Top issues

Latest release

v1.5.3 v1.5.3 2025-07-04
Highlights

gsplat.rasterization now supports render a batch of scenes in one pass. [In addition to its original support of rendering a batch of cameras per scene]

 What's Changed
 Link Jonathan's Tutorial by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/688
 Fix format README.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/689
 Update README.md by @liruilong940607 in https://github.com/nerfstudio-project/gsplat/pull/690
 Batchify all APIs by @JunchenLiu77 in https://github.com/nerfstudio-project/gsplat/pull/670
 fix bug in gsplat-b

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON