Awesome-Gaussian-Skills

Awesome Gaussian Skills

The Most Comprehensive 3D Gaussian Splatting Catalog — 1011 methods, 26 Categories, Interactive Explorer

You shouldn't search 20 repos for 3DGS papers. This is the only one you need.

English | 中文

Table of Contents

• Why This Repo?
• Live Demo
• Quick Start
• Integrations
• Online Book
• What's New (Oct 2026)
• Knowledge Base
• 18 AI-Powered Skills
• Visualization Samples
• Research Innovation Highlights
• Roadmap
• Architecture
• SplatVerse Studio
• Contributing
• Citation
• Ecosystem & Acknowledgments
• License
• Sponsor & Community
• Star History

Why This Repo?

Other awesome lists give you paper titles. We give you paper titles + an AI toolkit that makes you faster. The canonical lists catalog the ecosystem for humans; this repo makes it consumable by AI agents — let your AI read the papers for you.

What You Need · Other Lists · This Repo 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 · 104 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 · 40+ method conversion pipeline Patent filing · Manual from scratch · Auto-generated claims & specs

Live Demo

Try the Interactive Method Explorer →

Search 1011 Methods instantly, filter by category, sort by citations, click any method card for details.

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"*

Integrations

This repo ships as both AI agent skills and an MCP server, so it works across agent runtimes and MCP clients — the knowledge base is consumable by your AI agent, not just by you:

Client · How to use Claude Code / OpenClaw · /plugin marketplace add jaccen/Awesome-Gaussian-Skills → install gaussian-research, gaussian-engineering, or gaussian-domain (18 skills in 3 plugins); or load skills/ directly (see CLAUDE.md); MCP server via the config below DSH (DeepSeek Harness) · dsh plugin --profile web add jaccen/Awesome-Gaussian-Skills — the 18 skills + MCP renderer auto-mount via cordis.patch.yml Claude Desktop / Cursor / Cline · copy the MCP stdio config from .marketplace/mcp-servers/client-configs.md Any MCP client · command: node, args: [/path/to/mcp-server/dist/index.js], transport: stdio — 34 tools (21 core + 13 experimental)

The MCP server exposes 34 tools — 21 core (import_scene, set_camera, modify_gaussians, render_frame, sculpt_pipeline, SLAT latent editing, …) + 13 experimental stubs — see mcp-server/README.md and .marketplace/mcp-servers/mcp-metadata.json.

📖 Online Book: Spatial & Embodied Intelligence

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 — 13 chapters + hands-on prelude & capture SOP, every method name anchored to this repo's real data (1011 Methods, 26 categories, 18 skills), zero fabrication

# · Chapter · Focus 引言 · Why this book · Why 3DGS is the key puzzle piece of Physical AI 前 · Landing prelude: should you, can you · Tech-selection matrix, eight cases where you should NOT use 3DGS, three reading paths CH 01 · NeRF → 3DGS: A paradigm leap · Explicit vs implicit, the three innovations, the alpha-compositing formula CH 02 · The math & engineering core · Anisotropic Gaussians, differentiable rasterization, adaptive density control, CUDA 操 · Data-capture SOP · Device selection, trajectory design, seven exposure hard rules, scale calibration —the first step that decides your quality ceiling CH 03 · From scene to world · Large-scale, dynamic/4D, GS-SLAM, compression & deployment CH 04 · Semantic Gaussians · CLIP/DINO feature distillation, open-vocabulary 3D segmentation CH 05 · Editing · Generation · Asset-ization · Feed-forward reconstruction, SDS generation, animatable assets, PBR relighting CH 06 · Embodied intelligence basics · VLA lineage (RT/π0/GR00T/ReconVLA), simulation, Sim2Real CH 07 · 3DGS as robot spatial memory · GS-SLAM, map-as-renderer, three tiers of spatial memory CH 08 · Object-level & articulated understanding · Part-level Gaussians, URDF bridging, the CAD·Mesh·3DGS triangle CH 09 · Agent-driven digital twins · MCP rendering pipeline, gesture interaction, the perception-action loop CH 10 · World models & the future · Six schools of world models, 3DGS×World Model, spatial foundation models, Physical AI CH 11 · Security, provenance & copyright · 3DGS watermarking, GaussTrace forensics, adversarial attacks, IP management CH 12 · Capture-to-delivery: the end-to-end pipeline · Ten-stage tool selection & pitfalls, formats & coordinate systems, cost/duration estimates, project failure modes CH 13 · Industry playbooks: six verticals · Museums & tourism, e-commerce, industrial inspection, AD simulation, embodied robots, surveying & mapping 附 · Appendix · Datasets, evaluation metrics, delivery-metric conversion & acceptance-report templates 实 · Practice index: from book to engineering · 18 engineering skills · 34 MCP tools · 1011+ method explorer, chapter-to-runnable-resource mapping 后记 · Will 3DGS be eaten? · Why explicit representations will be compressed, not consumed

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.

Why we wrote it (and how it relates to this repo)

This book is the *narrative layer* over the repo's *data layer*. The repo gives you 1011 method names, abstracts, and 18 engineering skills —but not the through-line that connects them. The book supplies that through-line: it argues *why* 3DGS became the bridge between spatial intelligence and embodied intelligence, and walks every chapter back to concrete methods and skills you can use today. Read the book to understand the map; use the repo to ship the territory.

What's New (Oct 2026)

Latest Update (Oct 19, 2026): v0.9.12 — Full-Library Audit + arXiv Scan: 21 New Methods (955 → 1011) ⭐

Full-library audit plus a fresh arXiv scan admitted 21 new indexed 3DGS methods, taking the library from 955 to 1011 (+21, +2.2%) across 8 categories — led by Compression & Streaming (+5), Cross-Domain (+3), Autonomous Driving (+2), World Models & Spatial Intelligence (+2), SLAM (+2). Every admitted method name is self-stated in its own paper's title/abstract (R9 protocol) and indexed; 13 candidates were rejected (no self-stated method name, survey, NeRF, or 3DGS used merely as a tool); one name collision (X-Splat) kept the existing entry and dropped the newcomer.

Audit fixes: one mis-attached description (STC-GS — corrected to its real contribution, a spatio-temporal coherent GS for weather-radar sequence prediction) and 16 blank descriptions backfilled. Full arXiv-ID re-verification across 1,462 unique IDs (1,461 reachable; the single unresolved ID was a historical note rather than a live record). All data carriers (methods.json / CSV / methods.html / abstracts.js / reference docs) re-verified at 1011, name sets identical. See changelog.

Previous Update (Oct 15, 2026): v0.9.11 — Research Expert Team Deep Expansion: Methodology Core + 15 Master-Paper Studies ⭐

Pure skill-content release — no carrier changes (955 methods / 26 categories / 18 skills stay). research-expert-team grew from a nine-role router into a two-layer methodology asset:

• Methodology core (program layer) — executable procedures distilled from 15 top-cited

exemplars: topic-selection engine (M1-M4 + five opening-sentence variants), argumentation skeletons (T1-T3 + representation-paper techniques B.5), 16 experiment patterns (C1-C16), eight reviewer must-ask questions with preempts (D1-D8), nine value amplifiers.

• Master-paper evidence base (5 directions, 15 papers) — full-text dissections of Kimera,

ConceptGraphs, ReAct, MetaGPT, Toolformer, Generative Agents, Voyager, DreamFusion, DreamGaussian, 3DGS, 4DGS, SuGaR, NeRF, Instant-NGP, DUSt3R (citations verified via Semantic Scholar).

• 3DGS paper-drafting blueprint — three writing rules (motivation upgrade / symbol

unification / painpoint→resource-metric mapping), five-section placement table, and a pre-submission checklist, fused with cg-paper-writing templates.

• Expert-review audited — all 10 re-fetched papers' numeric claims line-verified; 2025-2026

latest-paper landscape notes added per direction.

Also fixed a pre-existing badge caliber bug (skills count 17 → 18; CN README was stale at 15). See the work log in changelog/2026-10-15.md and the release record changelog/2026-10-15-v2.md.

Previous Update (Oct 13, 2026): v0.9.10 — AIGC Content Creation Category + Research Expert Team Skill ⭐

New category AIGC Content Creation (22 methods; taxonomy 25 → 26): the AI-generated-content creation layer over 3DGS — text/image → 3DGS scenes and assets, generative scene reconstruction, stylization, artistic fonts, avatars. Anchored by DiffSplat, Dragen3D, PSGS, Lyra, CSD, SplatFont3D plus 2026 entries (VirSqueezer, CGGS, UniWorld-View, OmniStyle-INR, Flex4DHuman, LightHarmony3D); the pre-existing CGGS entry was completed with its arXiv ID (2607.03819) and re-categorized. New skill `research-expert-team` (17 → 18 skills): a nine-role full-cycle research team — idea evaluation, innovation mining, simulated peer review, academic polishing, AIGC-trace hygiene (publication hygiene), framework & venue compliance, strict venue-format writing, experiment design, experiment analysis — with method-selection tables for the three frontier directions (Ontology / Super Agents / AIGC Content Creation). Library 934 → 955; all data carriers re-verified at 955, name sets identical. See changelog.

Previous Update (Oct 13, 2026): v0.9.9 — Knowledge-Base Expansion: 900 → 934, Two New Skills ⭐

34 new indexed methods admitted, taking the library from 900 to 934, with the taxonomy growing 23 → 25 categories: two new cross-cutting categories — *Ontology & Knowledge Representation* (12 methods) and *Super Agents & Agentic AI* (20 methods). Two new skills shipped — ontology (3D scene graphs, spatial ontologies, neuro-symbolic reasoning) and super-agent (multi-agent LLM system design, 3D/spatial agent integration) — skill count 15 → 17. CGS-SLAM name-collision remediated (colliding newcomer dropped; original IROS 2025 entry restored). All data carriers re-verified at 934, name sets compared entry by entry; site-wide caliber unified to 934 / 25 / 17. See changelog.

Earlier updates (v0.9.8 and before)

Previous Update (Oct 20, 2026): v0.9.8 — World Models Category Reinforcement (896 → 900) ⭐

Targeted reinforcement of the thinnest category. 4 new indexed 3DGS-based World Model / Spatial Intelligence methods admitted, taking the library from 896 to 900. The World Models & Spatial Intelligence category grew from 8 → 12 methods: HY-World 2.0, F3DGS (federated multi-agent world modeling), 4DGS-WAM (object-centric world action model), Cloth-Splatting (3DGS cloth state estimation). Two missing arXiv IDs backfilled (Holi-Spatial → 2603.07660, Spatial-TTT → 2603.12255); two entries flagged unverified pending source check (APEIRIA, S²AM3D). GSMem found already in library under Embodied AI & Robotics — not duplicated. See changelog.

Previous Update (Oct 12, 2026): v0.9.7 — Manual Admission: 15 New Methods (881 → 896) ⭐

Manual admission of 15 new indexed 3DGS methods, taking the library from 881 to 896 (+15, +1.7%). Admissions span 9 categories: Acceleration (H2-Ray, TileSkipper, SplatQ), Feed-Forward (CompactSplat, DeltaSplat, DensiTok), Embodied AI & Robotics (Splat2Act, 2DGS-Planner, NovaSplat), plus OuroWorld (Dynamic & 4D), PAM-ToD (HDR & Relighting), FlyMark (Security), GSCV (Compression & Streaming), OpenSplatGraph (Language & Semantic), PCAsplat (Surface & Rendering). Every admitted method name is self-stated in its own paper's title/abstract (R9 protocol) and indexed. 12 candidate papers were rejected for lacking a self-stated method name, being benchmark-only, NeRF (not 3DGS), or using 3DGS merely as a tool. All data carriers (methods.json / CSV / methods.html / abstracts.js / reference doc) re-verified at 896, name sets compared entry by entry. No method name was fabricated.

See changelog/2026-10-12.md for the full admission list.

Update (Oct 7, 2026): v0.9.6 — Manual Admission: 9 New Methods (872 → 881) ⭐

Manual admission of 9 new indexed 3DGS methods, taking the library from 872 to 881 (+9, +1.0%). Admission includes Speedy-Splat (CVPR 2025, precise tile intersection + efficient Hessian-based pruning, 6.71× render speedup) and 8 recent September 2026 papers: AESplat (pose-free feed-forward), AGILE-GS (anchor-guided NBV), OC-GS (irregular turntable), ClearGS (handheld video), ChronoFuseGS (multi-temporal fusion, PG 2026), TangoGS (cross-scale compact), RRTO-CF3DGS (COLMAP-free), Observation-Gram (SH compression). All data carriers (methods.json / CSV / methods.html / abstracts.js / reference doc) re-verified at 881, name sets compared entry by entry. No method name was fabricated.

See changelog/2026-10-07.md for the full admission list.

Update (Sep 21, 2026): v0.9.5 — Daily arXiv Scan: 13 New Methods (859 → 872) ⭐

Routine daily arXiv scan admitted 13 new indexed 3DGS methods, taking the library from 859 to 872 (+13, +1.5%). Admissions span Surface & Rendering, Feed-Forward, Large-Scale, Compression, Sparse-View, Cross-Domain, Embodied AI & Robotics, Dynamic, and Language & Semantic categories (incl. LiteTex-GS, GrapeSplat, VDGS, CRP-GS, NormLift). 7 candidate papers were rejected for failing the verification protocol — benchmarks without a self-stated method name, descriptive-only paper titles, or 3DGS used merely as a tool. All data carriers (methods.json / CSV / methods.html / abstracts.js / reference doc) re-verified at 872, name sets compared entry by entry. No method name was fabricated; the library's "every entry arXiv-verifiable" guarantee holds.

See changelog/2026-09-21-v3.md for the full admission list.

Update (Sep 21, 2026): v0.9.4 — Multi-Channel Harvest: 700 → 859 Methods + Accuracy Overhaul ⭐

Knowledge base expanded from 700 to 859 verified methods (+159, +22.7%) through a multi-channel arXiv harvest over the last 150 days. Six query families (cs.CV / cs.GR / cs.RO / full-corpus / abs:"3D Gaussian Splatting" / ti:"Gaussian Splatting") returned 395 candidates; after verification 162 were admitted. Also in this release:

• Verification protocol (R1–R6): every admission requires the paper's *self-stated* method name,

reproduced in its own abstract; multi-word names must contain a proper-noun token — this alone rejected 67 descriptions masquerading as method names (Capacity-Controlled, Scene-Level). 114 borderline candidates were read individually; 25 adjudicated in, the rest dropped.

• Accuracy repairs: 57 reference links had a displayed arXiv ID differing from the hyperlinked one

(all had the correct ID displayed, wrong link). 13 mis-attributed entries deleted — e.g. Dynamic 3D Gaussians pointed at 2309.13114, which is actually a magnetic spin-glass physics paper, and GS-LRM-v2 pointed at DOF-GS. All now verified against the arXiv API.

• AIGC traces removed from 29 text files; 21 historically corrupted JPEGs restored and re-stripped safely.
• `README_CN.md` recovered from double-encoding corruption that had mangled every Chinese string.
• Full carrier sync — methods.json / CSV / methods.html / abstracts.js / reference doc

all verified at 881, name sets compared entry by entry rather than by count alone.

Adjudication wave (same day). A second pass resolved every name carrying a derived suffix or colliding with another entry: Scaffold-GS+ and GaussianSplatting-SLAM-v2 deleted (no such paper exists), Luminance-GS++ renamed to its self-declared base name, and Spark 2.0's description corrected — it is World Labs' open-source WebGL2 splat renderer, not an NVIDIA robotics simulator. Two independent papers both self-name GeoGS-SLAM (2607.07452 and 2607.11184, disjoint author lists); they are two methods, not a sequel, and are now disambiguated. 862 → 859.

See changelog/2026-09-21.md and changelog/2026-09-21-v2.md for the full audit trail.

Latest update (Sep 20): v0.9.2 —Scene Agent + Mapmost Engineering Wave: 5 New Methods + 6 Skill Enhancements. Knowledge base expanded from 692→ 97 methods. Added 5 scene-generation Agent papers: SceneSmith (ICML 2026 Spotlight, MIT CSAIL —hierarchical designer-critic-orchestrator VLM agents for simulation-ready indoor scenes), Scenethesis (ICLR 2026, NVIDIA —training-free LLM+vision agentic framework), SceneGenAgent (ACL 2025 —LLM coding agent for industrial scenes), SceneConductor (arXiv —multi-agent orchestration from single image), SceneAssistant (arXiv —visual-feedback agent for open-vocabulary scene generation). Injected Mapmost production engineering knowledge into 4 skill files: 3DGS individualization (单体化) in best-practices.md, LOD streaming + seam-fix + adaptive partition training in best-practices.md, 3DGS+3DTiles multi-source fusion in gis-toolchain.md, LUT color grading in tech-stack.md, Mapmost as Digital Twin player with 100km² benchmark in industry-landscape.md. Categories updated: Generation +4, Embodied AI & Robotics +1.

Previous (Sep 20): v0.9.1 —ECCV 2026 Wave: 14 New Methods. Knowledge base expanded from 678→ 92 methods. All 14 new entries indexed or ECCV-official: Wat3R (underwater 3D geometry without annotations), GeoNVS (geometry-grounded video diffusion with GS-Adapter), Edit3r (instant 3D editing from unposed images), SA-ResGS (first residual learning for 3DGS in next-best-view selection), GaussianLens (on-demand localized high-res reconstruction), Deformable Triangle Splatting (non-convex primitive with per-edge control points), Neural Harmonic Textures (per-primitive harmonic feature decoding), CubicSplat (error-bounded differentiable vector graphics), TetraSDF (analytic isosurface extraction), Heat Kernel Textures (ECCV 2026 Best Paper —geodesic Gaussians), GRF-Recon (long-sequence feed-forward with global ray-field), PriSplat (distractor-free 3DGS via multi-view propagation), Per-View Distractor Filtering (training-free feed-forward artifact removal), GS-Underwater (controlled cross-regime underwater benchmark study). Categories updated: Surface & Rendering +5, Feed-Forward +4, Cross-Domain +2, Robustness +2, Editing +1, Embodied AI & Robotics +1. All data carriers in sync.

Previous (Sep 16): v0.9.0 —Data Accuracy Release. Full-library audit of every entry against the arXiv API: each arXiv ID re-verified reachable and matched to its paper (method name must appear in the title/abstract). 181 entries failed verification and were removed, 56 wrong-ID entries re-linked to their real papers, 5 renamed to the papers' self-declared method names, plus 1 duplicate removed. The count is now honest instead of inflated: 678 methods, 23 categories, 568 indexed (83%), 130 code links (19%). Per-entry audit evidence: docs/data-accuracy-audit-2026-09-16.md. See changelog/2026-09-16-v5.md.

Previous (Sep 4): **v0.8.3 —Dynamic Scene Survey In