3DGS/CAD/Mesh domain-specific spatial intelligence agent: scene-level reasoning, CAD-in-the-loop parametric extraction, multi-modal 3D interaction.
Generate publication-quality visualizations for 3DGS research: radar charts, comparison tables, method timelines. Supports both static (PDF/PNG) and interactive (HTML) output.
Generate CN patent docs (claims, specification, abstract) and software copyright materials from AI/big-data project code or docs.
Design rigorous experiments for 3D Gaussian Splatting research papers. Recommends datasets, baselines, metrics, ablation matrices, and visualization plans tailored to your method.
Guide for deploying 3D Gaussian Splatting from research to production: industry use cases, engineering pipelines, tool selection, and deployment best practices
Diagnose and fix 3DGS training-time failures: NaN losses, OOM crashes, divergent optimization, floater artifacts, densification failures, hyperparameter sensitivity.
Review 3D Gaussian Splatting implementation code for correctness, performance bugs, and best practices.
Read and summarize 3D Gaussian Splatting research papers. Extracts method architecture, core innovations, experimental results, and key findings from arXiv papers or local PDFs.
Signed Gaussian Splatting & TPSC (Transmittance-Preserving Subtractive Compositing): negative-opacity Gaussians that subtract color without consuming transmittance.
Academic paper writing skill for 3D vision, computer graphics, CAD, and 3D understanding. Covers NeRF, 3DGS, SLAM, point cloud processing, 3D shape understanding/generation, CAD…
MCP protocol integration with 3DGS rendering pipeline: Agent-controlled Three.js/WebGPU rendering, voice-driven scene reconstruction, real-time parameter manipulation.
3DGS Articulated Object Reasoning & Digital Twin Agent. Reason about articulated objects in 3DGS scenes: extract part structure, infer kinematic constraints, generate interactive…
Compare 3D Gaussian Splatting variants across multiple dimensions. Generates detailed comparison tables covering primitive representation, rendering formulation, training…
Bridge CAD, Mesh, and 3D Gaussian Splatting representations. Covers mesh↔3DGS conversion, surface extraction from Gaussians, CAD reverse engineering with 3DGS, B-rep/parametric…
AI-native IP skill: generate patent applications, software copyright materials, or technical disclosures from AI project code/papers/docs, with direct Word and PPT output.
Migrate NeRF-based methods to 3D Gaussian Splatting with step-by-step guidance. Analyzes component compatibility, provides code templates, and identifies potential issues.
3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD,…