jaccen/awesome-gaussian-skills

Why This Repo?

Other awesome lists give you paper titles. We give you paper titles + an AI toolkit that makes you faster.

Live Demo

Try the Interactive Method Explorer →

Search 783+ Methods instantly, filter by category, sort by citations, click any method card for details.

📖 Online Book: Spatial & Embodied Intelligence (New!)

** NEW (Jul 2026)** — A full open-source technical book, built around 3D Gaussian Splatting as the spine and weaving together spatial intelligence and embodied intelligence into one closed loop: representation → perception → planning → action.

📖 Read the Book →

Core formula (echoing Agent = LLM + Context + Tools):

Embodied Agent = Spatial Representation × Perception × Planning × Action

What’s inside — 12 chapters, every method name anchored to this repo’s real data (783+ Methods, 23 categories, 15 skills), zero fabrication:

Each chapter ends with hands-on exercises and links back to the repo’s method tables, references/, and skills — so reading the book and doing the engineering are one seamless flow.

Highlights you won’t find in a paper list:

• The six schools of world models (2026 taxonomy) and where 3DGS sits as the only representation that is simultaneously renderable, differentiable, and editable.
• How GS-World, ManiGaussian, and OrbiSim turn 3DGS into a differentiable simulation engine.
• A three-tier model of robot spatial memory (geometric → appearance → semantic) and where current GS-SLAM actually stands.

What’s New (Aug 2026)

Latest update (Aug 7): v0.8.0 — Platform Upgrade (P0+P1+P2). Knowledge layer: single source of truth (data/methods.json, 783 methods, 23 categories) with data CI; 5 fabricated entries purged; 14 arXiv-verified frontier methods added. Capability layer: true-3DGS render loop (gsplat via HTTP-served PLY), server-authoritative scene persistence, real PLY/SPLAT export, 5 distinct prune strategies, grid-accelerated ray query, runtime arg validation, WS origin allowlist, 21 unit tests. Platform layer: Benchmark arena (bench/), skill orchestration contracts (skills/_contracts/), Router manifest loader (scripts/router_load.py). 13 core MCP tools (all real) + 13 experimental (gated by INCLUDE_EXPERIMENTAL=1). See changelog/2026-08-07.md.

Previous (Jul 26): v0.5.1 — Full Method Audit & 14 New Methods. Now 789+ Methods (775 verified unique baseline + 14 new). Full re-audit across 11 source files; all method counts unified to 789+. New additions: GrainGS (dynamic, 36.98 dB / 435.6 FPS / 4.67 MB), GLAM-SLAM (IROS 2026, outdoor decoupled SLAM), SubSplat (subpixel feed-forward), ATSplat (adaptive 3D tokens, 1136 FPS), 3D-GIMP (3DGS inpainting), LB-Edit (7× lower editing latency), FlexiAvatar (ECCV 2026, visible-body-only optimization), ZeroSplat (ECCV 2026, training-free segmentation), CaT-GS (CVPR 2026, 10× faster rendering), FF-ProCams (projector-camera inverse rendering), i3dgs (SIGGRAPH 2026, large-scale unordered), VIGS-SLAM (ECCV 2026, iPhone real-time), ECoNGS (IEEE VIS 2026, volume visualization), AniGS (scene-level animation via diffusion prior). +MoDE/MoE-GS code link. Previous (Jul 24): v0.5.0 MCP Protocol Implementation. Previous (Jul 23): v0.4.3 ICML 2026 & Material/Provenance Wave — GaussTrace (ICML 2026), GADA (ICML 2026), InvSplat, MGM, DualPhys-GS, StereoGS. v0.4.4 added 3dgs-training-debugger skill (60+ runtime patterns).

Full changelog: changelog/

Quick Start

Each skill is a standalone SKILL.md file — copy it to your Agent’s skills directory.

3 commands to your first AI-powered 3DGS workflow:

git clone https://github.com/jaccen/Awesome-Gaussian-Skills.git

# Option 1: Claude Code
cp -r Awesome-Gaussian-Skills/skills/* .claude/

# Option 2: Cursor
cp -r Awesome-Gaussian-Skills/skills/* .cursor/rules/

# Option 3: One-Click Install
curl -sSL https://raw.githubusercontent.com/jaccen/Awesome-Gaussian-Skills/main/scripts/setup.sh | bash

Then ask your Agent: “Compare 3DGS and 2DGS rendering formulations”

Knowledge Base (783+ Methods, 23 Categories)

Download full database: CSV | Full analysis: references/3dgs-methods-overview.md

15 AI-Powered Skills

Works with Claude Code, Cursor, Windsurf, and other AI Agent frameworks.

Visualization Samples

Generated by 3dgs-visualizer — see Test/ for full-resolution files.

Research Innovation Highlights

Derived from systematic gap analysis across 783+ Methods. Target venues: TVCG / CGF / CAD / T-RO / IJCV / ACM TOG.

Roadmap

• [x] v0.1 — Initial release with 6 core skills (Apr 2026)
• [x] v0.2 — 3dgs-visualizer + Text2Word demo (May 2026)
• [x] v0.3 — Knowledge base 665->789+ Methods, 25 Categories, 101+ bug patterns, 12 skills (Jun 2026)
• [x] v0.3.6 — Spatial intelligence wave: 680->639+ methods, +10 new methods (FastGS, Holi-Spatial, Spatial-TTT, etc.), Dimension 11, Anthropic standard alignment (Jun 25, 2026)
• [x] v0.3.6 — CVPR 2026 representative papers: 690->639+ methods, +23 verified new methods, all 13 skills updated (Jun 28, 2026)
• [x] v0.4.0 — Router Architecture Expansion: cg-paper-writing + 3dgs-engineering-guide → Router + manifest.yaml + static/; 3dgs-code-reviewer Self-Check Loop; cg-paper-writing Stage Gates; 3 Router skills total (Jul 2, 2026)
• [x] v0.4.1 — ECCV & ISCA 2026 Wave: +Flux-GS, AnchorSplat, ASSEMCAD, WildSplat, NoDrift3R (ECCV 2026), Axis-Shared Rasterization Accelerator (ISCA 2026), Provable Pruning via Coresets; 639+ methods (Jul 9, 2026)
• [x] v0.4.2 — SIGGRAPH & MICCAI 2026 Wave: +DP-Splat, MoE-GS/MoDE (TPAMI 2026), HyperGS, MAC-Splat (ECCV 2026), Track2Map (MICCAI 2026), PEAR (SIGGRAPH 2026), CoSAG, HoloTetSphere (ECCV 2026), SalientGS; 639→789+ Methods, +3dgs-compression-deploy skill, 14 skills total (Jul 14, 2026)
• [x] v0.4.3 — ICML 2026 & Material/Provenance Wave: +GaussTrace (ICML 2026), GADA (ICML 2026), InvSplat, MGM, DualPhys-GS, StereoGS; 660→789+ Methods, +3 bug patterns (108+ total), MCP roadmap v0.2.3 (Jul 23, 2026)
• [x] v0.4.4 — Training Debugger Skill: +1 skill (3dgs-training-debugger, 60+ runtime patterns, VRAM management, convergence analysis), 14→15 skills total (Jul 23, 2026)
• [ ] v0.4 — 3dgs-spatial-agent enhancements (knowledge-constrained CAD, DDF-GS ray query)
• [x] v0.5.0 — MCP Protocol Implementation: 24-tool MCP server (mcp-server/), Three.js WebSocket renderer, 24-pattern voice intent mapper, headless mode, voice demo (Jul 24, 2026)
• [x] v0.5.1 — Full Method Audit & 14 New Methods: 775 verified unique baseline + 14 new = 789+ methods; all method counts unified across 11 source files; +GrainGS, GLAM-SLAM, SubSplat, ATSplat, 3D-GIMP, LB-Edit, FlexiAvatar, ZeroSplat, CaT-GS, FF-ProCams, i3dgs, VIGS-SLAM, ECoNGS, AniGS (Jul 26, 2026)
• [x] v0.8.0 — Platform Upgrade (P0+P1+P2): single source of truth (data/methods.json, 783 methods, 23 categories, data CI); 5 fabricated entries purged + 14 arXiv-verified frontier methods; true-3DGS render loop (gsplat via HTTP-served PLY); server-authoritative scene persistence; real PLY/SPLAT export; 5 prune strategies; grid-accelerated ray query; runtime arg validation; WS origin allowlist; 21 unit tests + 2 CI workflows; Benchmark arena (bench/); skill orchestration contracts (skills/_contracts/); Router manifest loader (scripts/router_load.py); 13 core MCP tools + 13 experimental (Aug 7, 2026)
• [ ] v1.0 — CI/CD integration + multi-framework official listings
• [ ] v2.0 — Agent-to-Agent collaboration (multi-agent paper discussion)

Full version history: changelog/

Architecture

Awesome-Gaussian-Skills/
├── data/                      # Single source of truth (methods.json, categories.json)
├── skills/                    # 15 AI Agent skills (SKILL.md format)
│   ├── _contracts/            # Inter-skill I/O schemas (paper-insight, comparison-report, experiment-plan)
│   ├── 3dgs-paper-reader/     # Paper reading & summarization
│   ├── 3dgs-method-compare/   # Method comparison engine (Router)
│   ├── 3dgs-code-reviewer/    # Code review (104 bug patterns)
│   ├── 3dgs-experiment-planner/ # Experiment design
│   ├── nerf-to-3dgs-migrator/ # NeRF→3DGS migration
│   ├── cad-mesh-3dgs/         # CAD/Mesh/3DGS bridge
│   ├── cg-paper-writing/      # CG paper writing assistant (Router)
│   ├── 3dgs-visualizer/       # Research visualization
│   ├── 3dgs-engineering-guide/ # Engineering deployment (Router)
│   ├── patent-software-ip/    # Patent & copyright generation
│   ├── 3dgs-spatial-agent/    # Spatial intelligence agent
│   ├── 3dgs-mcp-renderer/     # MCP rendering bridge
│   ├── 3dgs-articulated-reasoner/ # Articulated reasoning & digital twin
│   ├── 3dgs-compression-deploy/  # Compression & deployment
│   └── 3dgs-training-debugger/  # Training failure diagnosis
├── mcp-server/                # MCP server v0.8.0 (13 core + 13 experimental tools, gsplat render loop, HTTP+WS :9842)
├── bench/                     # Benchmark arena (metrics.py, run_eval.py, leaderboard.json)
├── scripts/                   # build_knowledge_base.py, validate_knowledge_base.py, router_load.py, validate_skill_contract.py
├── studio/                    # SplatVerse Studio (bridge + web)
├── docs/                      # GitHub Pages interactive explorer
├── references/                # Knowledge base (783+ Methods, 23 Categories)
├── Test/                      # Visualization samples
├── changelog/                 # Version history
└── assets/                    # Project images

Each skill follows the SKILL.md standard, compatible with Claude Code (.claude/), Cursor (.cursor/rules/), Windsurf, and other AI Agent frameworks.

SplatVerse Studio: Short Video Creation

SplatVerse Studio integrates 3D Gaussian Splatting with a short-drama pipeline powered by the Toonflow engine, letting you go from text scripts to 3DGS-rendered video scenes.

Architecture

Toonflow Engine (:10588)          SplatVerse Studio
┌──────────────────────┐         ┌───────────────────────────┐
│  Script → Assets →    │  REST   │  Bridge (:10590)          │
│  Storyboard → Video   │◄──────►│  ├─ Project Browser       │
│                       │         │  ├─ Render Studio          │
│  Vendor: 3dgs-renderer│         │  ├─ MCP Tools (25 tools)  │
└──────────────────────┘         │  │  MCP Renderer (:9842)  │
                                  │  ├─ Pipeline (7 steps)     │
 MoneyPrinterTurbo (:8501)       │  │  ├─ Script Adaptation   │
┌──────────────────────┐         │  │  ├─ Storyboard          │
│  Online material →    │  REST   │  │  ├─ Toonflow Sync       │
│  TTS → FFmpeg → Video │◄──────►│  │  ├─ TTS Dubbing         │
│  Cross-platform post  │         │  │  ├─ Video Gen           │
└──────────────────────┘         │  │  ├─ FFmpeg Compose      │
                                  │  │  └─ Publish (MPT)       │
                                  │  Studio Web (:5173)        │
                                  └───────────────────────────┘

Quick Start

Prerequisites: Node.js ≥ 18, Toonflow app installed at ../AI应用/Toonflow-app

# 1. Start all services (Toonflow + MCP Server + Bridge + Studio Web)
npm run prod:full

# 2. Open Studio Web
#    http://localhost:5173

If you only need the 3DGS rendering tools without Toonflow:

npm run dev    # MCP + Bridge + Web, no Toonflow

Creating a Short Video: Step by Step

Step 1 — Write a Script in Toonflow

Open the Toonflow web app (typically at http://localhost:10588). Create a project, write a script, and generate storyboards. Each storyboard is a scene with:

• Prompt — text description for image/video generation
• Duration — scene length in seconds
• Track — scene grouping label

Toonflow’s pipeline: Text → Script → Assets (roles, scenes, props) → Storyboards → Video

Step 2 — Browse Projects in Studio Web

Open http://localhost:5173 and navigate to Projects. You’ll see all Toonflow projects. Click a project to view its storyboards.

Step 3 — Render Storyboards as 3DGS Scenes

Two rendering modes in Render Studio (/render):

For batch rendering, enter the Toonflow Project ID and Storyboard IDs (comma-separated), then click Render Batch. The Bridge fetches storyboards from Toonflow, builds 3DGS scenes via MCP Server, and renders each storyboard frame.

Step 4 — Monitor Render Progress

Render progress streams via SSE (Server-Sent Events). You’ll see toast notifications in the top-right corner as each storyboard renders. The Dashboard shows recent render tasks with progress bars.

Step 5 — 3DGS as a Toonflow Vendor (Optional)

To use 3DGS rendering directly inside Toonflow’s image/video generation:

# Copy the vendor adapter to Toonflow
cp studio/bridge/vendor/3dgs-renderer.ts ../AI应用/Toonflow-app/data/vendor/

This registers 3DGS as both an image model (single-frame render) and video model (multi-frame animation) in Toonflow’s vendor system.

Port Reference

Troubleshooting

• “Toonflow engine not running” — Start Toonflow: npm run prod:full or manually node data/serve/app.js in the Toonflow directory
• Projects page shows no storyboards — Create a script first in Toonflow; storyboards belong to scripts
• 3DGS vendor not available in Toonflow — Copy studio/bridge/vendor/3dgs-renderer.ts to Toonflow’s data/vendor/ directory

MoneyPrinterTurbo (MPT) Integration

MoneyPrinterTurbo is integrated as an optional HTTP API sidecar, extending SplatVerse Studio with online material video generation, additional TTS voices, and cross-platform publishing. Zero intrusion — when MPT_ENABLED=false or MPT_API_URL is unset, the pipeline behaves exactly as before.

What MPT Adds

Frontend Entry

The Studio Web “Script → Video” page (/pipeline) ships a built-in MPT entry:

• Config panel: a “🚀 MoneyPrinterTurbo Integration” group at the bottom of the model config section — enable toggle, service URL, material source, default voice, plus a live connection status (Connected / Not connected). Saving writes the settings into .env.
• Per-task options: a “🚀 MoneyPrinterTurbo Fallback” block at the bottom of the input section — check “Video fallback” and “TTS fallback” to automatically degrade to MPT when any main-pipeline step (3DGS / Toonflow / TTS) fails; when MPT is enabled you can also pick an MPT voice and publish platforms (TikTok / YouTube / Instagram).

Note: the bridge auto-loads the project-root .env at startup (dependency-free implementation, see studio/bridge/src/load-env.ts), so config saved from the UI takes effect after the bridge restarts. Launch the bridge from the project root (npm run dev:bridge or scripts/start-dev.ps1) to ensure the root .env is picked up.

Setup

# 1. Configure MPT (fill in at least one material API key)
cp mpt-config.example.toml mpt-config.toml
#    Edit mpt-config.toml — required: pexels.api_key or pixabay.api_key (both free)

# 2. Start MPT container
docker compose -f docker-compose.mpt.yml up -d

# 3. Verify MPT is running
curl http://localhost:8501/api/v1/tasks?page=1&page_size=1

# 4. Enable MPT in Studio .env
#    MPT_ENABLED=true
#    MPT_API_URL=http://localhost:8501

Configuration Reference

MPT-side settings (API keys for Pexels/Pixabay, TTS providers, LLM) go in mpt-config.toml, not .env. See mpt-config.example.toml for the full template.

API Endpoints

Creating a Task with MPT Fallback

curl -s http://localhost:10590/api/pipeline/tasks \
  -H "Content-Type: application/json" \
  -d '{
    "text": "In a quiet town, a kitten named HuaHua chats with a butterfly...",
    "title": "HuaHua Adventure",
    "style": "水彩",
    "videoRatio": "16:9",
    "enableTTS": true,
    "enableVideoGen": false,
    "enableMptFallback": true,
    "enableMptTTS": true,
    "mptVoiceName": "zh-CN-XiaoxiaoNeural",
    "publishPlatforms": [
      { "name": "tiktok", "title": "HuaHua Adventure", "tags": ["animation", "cat"] }
    ]
  }'

The 7-step pipeline: Script Adaptation → Storyboard → Toonflow Sync → TTS (MPT fallback) → Video Gen → FFmpeg Compose (MPT fallback) → Publish (MPT)

Contributing

Contributions welcome! See Contributing Guide.

Citation

@misc{awesome-gaussian-skills,
  author = {jaccen},
  title = {Awesome Gaussian Skills: 3D Spatial Intelligence Open-Source Toolbox for 3D Gaussian Splatting Research},
  year = {2026},
  url = {https://github.com/jaccen/Awesome-Gaussian-Skills}
}

Acknowledgments

• 3D Gaussian Splatting — The foundational work
• awesome-3D-gaussian-splatting — The awesome list that inspired this project
• Awesome3DGS/3D-Gaussian-Splatting-Papers — Comprehensive paper collection
• All 3DGS researchers whose papers form our knowledge base

License

Apache-2.0. See LICENSE for details.

Sponsor & Community

If this project helps your research or work, consider supporting us!

Star History