by jaccen
图形学与3DGS、空间智能持续更新论文;AI Agent Skills for 3D Gaussian Splatting, NeRF & Computer Graphics Research. 660+ methods, 25categories, 12skills. OpenClaw / Claude Code compatible.
# Add to your Claude Code skills
git clone https://github.com/jaccen/Awesome-Gaussian-SkillsGuides for using ai agents skills like Awesome-Gaussian-Skills.
Last scanned: 6/13/2026
{
"issues": [
{
"file": "README.md",
"line": 199,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -sSL https://raw.githubusercontent.com/jaccen/Awesome-Gaussian-Skills/main/\"",
"severity": "low"
}
],
"status": "PASSED",
"scannedAt": "2026-06-13T07:46:57.446Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Awesome-Gaussian-Skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by jaccen. 图形学与3DGS、空间智能持续更新论文;AI Agent Skills for 3D Gaussian Splatting, NeRF & Computer Graphics Research. 660+ methods, 25categories, 12skills. OpenClaw / Claude Code compatible. It has 104 GitHub stars.
Yes. Awesome-Gaussian-Skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/jaccen/Awesome-Gaussian-Skills" and add it to your Claude Code skills directory (see the Installation section above).
Awesome-Gaussian-Skills is primarily written in HTML. It is open-source under jaccen on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Awesome-Gaussian-Skills against similar tools.
No comments yet. Be the first to share your thoughts!
You shouldn't search 20 different repos for 3DGS papers. This is the only one you need — plus AI-powered tools that no other list has.
Latest update (Jun 5): 630+ → 660+ methods, 25 categories, 97+ bug patterns. +18 new methods including: ZipSplat (token-based feed-forward 3DGS, ~6x fewer Gaussians, +2.1dB PSNR), Geometry Gaussians (per-splat geometry opacity decoupling), 3DReflecNet (CVPR 2026, systematic benchmark for reflective/transparent 3D reconstruction), MeshFlow (CVPR 2026 Highlight, MeshVAE + Flow-based Diffusion Transformer), MeshWeaver (CVPR 2026, autoregressive next-vertex mesh generation), UniCAD (multi-modal multi-task CAD benchmark), Anchor3R (streaming 3D reconstruction with transient anchors), SimuScene (physics-in-the-loop compositional 3D reconstruction). Skills v0.3.1: 5 new bug patterns (#89-#93) + Token-based cluster in method comparison.
| Method | ArXiv | Category | One-Line Innovation |
|---|---|---|---|
| D4RT | 2512.08924 | Dynamic / 4D | CVPR 2026 Best Paper; unified query 4D reconstruction + tracking; 200+ FPS |
| TRELLIS.2 | — | Generation | CVPR 2026 Best Student Paper; 4B-param native 3D; 17s PBR generation |
| SAM 3D | — | Generation / Foundation | CVPR 2026 Honorable Mention; single-image 3D foundation model (Meta) |
| RAF | — | Physics / Simulation | CVPR 2026 Findings; bridges 3DGS and physics engines (MPM/SPH/PBD) |
| ReLaGS | 2603.17605 | Language / Semantic | Open-vocab 3D reasoning without per-scene training |
| FreeForm | 2605.29318 | Dynamic / Elastic | Particle-skinned eigenmodes for elastic deformation on 3DGS |
| FreeArtGS | 2603.22102 | Articulated | Articulated GS under free-moving scenario |
| PARTICULATE | — | Articulated / Feed-Forward | Feed-forward 3D object articulation from static mesh |
| DropAnSH-GS | — | Sparse-View | Anchor dropout + SH regularization for sparse-view 3DGS |
| BA-GS | — | SfM-Free | Bayesian Adaptive GS for SfM-free reconstruction |
| SR3R | — | Feed-Forward / SR | Super-resolution + feed-forward GS reconstruction |
| ZipSplat | 2606.05102 | Feed-Forward | Token-based 3DGS; ~6x fewer Gaussians; +2.1dB PSNR over pixel-grid methods |
| Geometry Gaussians | 2606.05124 | Surface / Rendering | Per-splat geometry opacity decoupling; signed-opacity direction |
| 3DReflecNet | 2605.10204 | Cross-Domain | CVPR 2026; systematic benchmark for reflective/transparent 3D reconstruction |
| MeshFlow | 2606.04621 | CAD / Generation | CVPR 2026 Highlight; MeshVAE + Flow-based Diffusion Transformer |
| MeshWeaver | 2606.04688 | CAD / Generation | CVPR 2026; autoregressive next-vertex mesh generation |
| UniCAD | 2606.05058 | CAD | Multi-modal multi-task CAD benchmark + universal model |
| Anchor3R | 2606.05035 | Feed-Forward | Streaming 3D reconstruction with transient anchors |
| SimuScene | 2606.03994 | Simulation | Physics-in-the-loop compositional 3D reconstruction |
| HiGS | 2606.00352 | Acceleration | Hierarchical tiles decouple partitioning/rasterization; 15.8x faster (NVIDIA) |
| DDF-GS | 2606.00817 | Rendering / GI | Directed Distance Field for ray queries on 3DGS; GI without mesh proxy |
| VEDAL | 2606.02346 | Compression | Variational free energy pruning; 5.2x compression @ 0.31 dB loss |
| 3DThinkVLA | 2606.04436 | Robotics | VLA with latent 3D priors via co-training |
| SymTRELLIS | 2606.04108 | Generation | Symmetry-aware 3D generation |
Full changelog: changelog/
Knowledge base curated with multi-source verification. Found an error? Open an Issue.
You shouldn't have to rebuild the same RAG pipeline for every new 3DGS paper, or manually compare 20 variants across 10 dimensions, or discover after submission that your CUDA kernel has a known bug.
With 660+ 3DGS papers since 2023 and growing, researchers waste hours on tasks that AI Agents can handle in seconds. Yet ClawHub's 13,000+ skills cover almost zero for 3D reconstruction or computer graphics.
| What You Do | Without This | With This |
|---|---|---|
| Read a new paper | 30–60 min manual skimming | Structured summary in seconds |
| Compare GS variants | Hand-build comparison tables | 10+ dimension auto-comparison |
| Review 3DGS code | Miss known bug patterns | 97+ pattern detection |
| Design experiments | Guess baselines & ablations | Venue-tailored experiment plan |
| Migrate NeRF → 3DGS | Trial-and-error porting | Step-by-step migration guide |
| What You Need | Typical Paper List | Awesome Gaussian Skills |
|---|---|---|
| Browse papers | Static markdown table | Interactive explorer: search, filter, sort |
| Compare methods | Open 2 papers side by side | 10+ dimension auto-comparison |
| Avoid code bugs | Discover after submission | 97+ known bug pattern detection |
| Design experiments | Guess baselines & ablations | Venue-tailored experiment plan |
| NeRF → 3DGS | Trial-and-error porting | Step-by-step migration guide |
| CAD ↔ 3DGS | No coverage | 52+ method conversion pipeline |
| Patent filing | Manual from scratch | Auto-generated claims & specs |
Bottom line: Other lists give you paper titles. We give you paper titles + an AI toolkit that actually helps you do research faster.
| Group | Categories | Key Topics |
|---|---|---|
| Core Representations | Foundation, Antialiasing, Optimization, Surface/Rendering, Image Rep. | 3DGS, 2DGS, Scaffold-GS, Mip-Splatting, GaussianImage... |
| Efficiency & Scale | Compression, Acceleration, Large-Scale, Feed-Forward | Compact-3DGS, BlitzGS, HiGS, VEDAL, VG²GT... |
| Understanding & Semantics | Language/Semantic, Generation, Autonomous Driving | LangSplat, DreamGaussian, StreetNVS... |
| Dynamic & Spatial | Dynamic, HDR, SLAM, Sparse-View | DSD-GS, WebSpline, GGD-SLAM, PanoPlane... |
| Applications | Human/Avatar, Editing, Relighting, CAD, Cross-Domain, Simulation, Robotics, and 14 more categories | AlbedoEdit, KDH-CAD, LEGS, TIDES, 3DEditSafe... |
Try the interactive method explorer — search 660+ methods instantly, filter by category, sort by citations.
Download full database: 3dgs-methods-overview.csv | Full analysis: references/3dgs-methods-overview.md
Core Representations
| Category | Description | Methods |
|---|---|---|
| Foundation | Core 3DGS representations and basic variants | 3DGS, 2DGS, Scaffold-GS, Scaffold-GS+, Mip-Splatting, 3DGEER, SNS |
| Antialiasing | Anti-aliasing and frequency-aware rendering | Mip-Splatting, LeanGaussian |
| Optimization | Training objectives, density control, and convergence | 3DGS-as-MCMC, 3DGS², AdpSplit, Denoising-GS |
| Surface / Rendering | Rendering formulation innovation (OIT, RBF, etc.) | SparseOIT, View-Dependent Splatting, Gaussian Surfel Rendering |
| Image Representation | Image-level Gaussian encoding | GaussianImage |
Efficiency & Scale
| Category | Description | Methods |
|---|---|---|
| Compression / Streaming | Lightweight, mobile, and progressive streaming | Compact-3DGS, Ligh |