jaccen

Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions. Detects 105+ known bug patterns including MoE-GS and Bayesian complexity control patterns. Use when: reviewing 3DGS/Gaussian Splatting CUDA code, debugging rendering artifacts, optimizing 3DGS training pipelines, checking loss function implementations, 代码审查/3DGS调试/性能优化.

Read and summarize 3DGS research papers. Extracts method architecture, innovations, experimental results from arXiv or local PDFs. Structured output with tables. Knowledge of 760+ methods across 25 categories. Use when: reading or analyzing a 3DGS/NeRF paper, extracting method details from arXiv PDF, summarizing 3D reconstruction research, 读论文/3DGS论文分析/文献总结.

3DGS Articulated Object Reasoning & Digital Twin Agent. Reason about articulated objects in 3DGS scenes: extract part structure, infer kinematic constraints, generate interactive digital twins. Use when: articulated object, digital twin, part structure, kinematic chain, URDF, interactive 3DGS, part-aware rendering, articulated manipulation, joint estimation, part segmentation 3DGS, ArtiSplat, ArtiTwinSplat, articulated reconstruction.

3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD, Web/WebGPU/mobile deployment, hardware acceleration (Tensor Core/GEMM/FPGA/ASIC), training-free semantic compression. Covers 53+ methods across 6 compression categories. Use when: compressing 3DGS models, deploying 3DGS to web/mobile/edge, selecting quantization bit-width, designing streaming pipelines, 3DGS压缩/量化/剪枝/部署/流式传输/移动端/硬件加速.

Guide for deploying 3DGS from research to production: 10 industry verticals, engineering stack, GIS toolchain solutions, cross-platform deployment, and common pitfalls. References 760+ methods. Use when: deploying 3DGS to production or industry, selecting tools/pipeline/platform, troubleshooting engineering problems (OOM, artifacts, platform lock-in), integrating 3DGS with GIS/BIM/ROS2/game engines, 3DGS部署/高斯泼溅工程化/3DGS生产环境/工程指南.

Design rigorous experiments for 3DGS research papers. Recommends datasets, baselines, metrics, ablation matrices. Targets CVPR/ICCV/ECCV/SIGGRAPH/TVCG. Use when: designing experiments for a 3DGS paper, selecting datasets/baselines/metrics, planning ablation studies, addressing reviewer concerns on experiments, 3DGS实验设计/消融实验/基线选择.

MCP protocol integration with 3DGS rendering pipeline: Agent-controlled Three.js/WebGPU rendering, voice-driven scene reconstruction, real-time parameter manipulation, light tracing backend. Use when: MCP rendering, agent-controlled 3DGS, voice-driven reconstruction, real-time 3DGS editing, Three.js 3DGS, WebGPU Gaussian splatting, interactive rendering control, speech-to-3D, light tracing, HiGS accelerated rendering.

Compare 3D Gaussian Splatting variants across 11 dimensions. Built-in knowledge of 760+ methods across 25 categories. Supports axis-driven fragment loading for efficient context usage. Use when: comparing 3DGS methods or variants, analyzing trade-offs between Gaussian Splatting approaches, generating comparison tables for 3DGS papers, finding the best 3DGS method for a scenario, 检索3DGS方法对比/3D高斯泼溅方法比较.

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. Covers 7 AI domains, 15 claim templates, patentability check, innovation mining, desensitization, prior-art search, and self-check.

Academic paper writing skill for 3D vision, computer graphics, CAD, and 3D understanding. Covers NeRF, 3D Gaussian Splatting, multi-view stereo, SLAM, point cloud processing, 3D shape understanding/generation, CAD modeling, reverse engineering, 3D scene understanding. Use when the user asks to write, refine, or polish academic papers in CG/3D vision venues (CVPR, ICCV, ECCV, SIGGRAPH, EG, PG, TVCG, CGF) or doctoral dissertations. Provides domain terminology conventions, reviewer concern analysis, experiment design guidance, and venue-specific writing patterns. Trigger on: paper writing, draft refinement, rebuttal, introduction/related work/methodology/experiment sections, abstract, contribution summary.