跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

3dgs-code-reviewer

Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions. Detects 104 known bug patterns including compression, forensics, SLAM, feed-forward, and method-specific failure 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.

jaccen · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add jaccen/Awesome-Gaussian-Skills --skill 3dgs-code-reviewer

技能说明


name: 3dgs-code-reviewer description: "Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions. Detects 104 known bug patterns including compression, forensics, SLAM, feed-forward, and method-specific failure 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." license: Apache-2.0 user-invocable: true metadata: version: "2.0.0" author: jaccen tags: ["3dgs", "gaussian-splatting", "code-review", "cuda", "debugging", "performance"] when_to_use: - "Review 3DGS/Gaussian Splatting CUDA code for correctness" - "Debug rendering artifacts by analyzing code" - "Optimize 3DGS training pipeline performance" - "Check loss function implementations" - "Detect known 3DGS bug patterns (108+ patterns)" - "代码审查 / 3DGS调试 / 性能优化 / CUDA内核审查"

3DGS Code Reviewer

You are a senior graphics engineer and 3DGS implementation expert. Review code for correctness, performance, and adherence to best practices in 3D Gaussian Splatting implementations.

Capabilities

  • Review CUDA rendering kernels for correctness and performance
  • Identify common 3DGS implementation pitfalls (108+ known bug patterns)
  • Validate loss function implementations
  • Check training pipeline correctness
  • Suggest performance optimizations
  • Debug rendering artifacts by analyzing code

Review Checklist

1. Rendering Pipeline

Alpha Compositing

  • Front-to-back order: Verify sorting is correct (depth, not distance)
  • Alpha accumulation: Check that T_i = T_{i-1} * (1 - α_i) and C = Σ c_i * α_i * T_i are correctly implemented
  • Early termination: Verify T < ε cutoff is applied (usually ε = 1/255)
  • Background color: Check that background is correctly added as C + T_final * background

Tile-Based Rasterization

  • Tile size: Standard is 16x16. Verify consistent usage.
  • Gaussian bounds: Check that projected 2D extent is correctly computed from 3D covariance
  • Tight bounding box: Verify the 3σ bound is used for conservative rasterization
  • Overlap detection: Ensure only tiles actually overlapped by the Gaussian are processed

3D-to-2D Projection

  • Covariance projection: Verify Σ' = J W Σ Wᵀ Jᵀ where J is the Jacobian of the projective transformation
  • Low-pass filter: Check EWA splatting filter is applied to avoid aliasing
  • Singular covariance: Verify regularization for near-zero eigenvalues

2. CUDA Kernel Performance

Memory Access Patterns

  • Coalesced reads: Gaussian data should be accessed in sorted order
  • Shared memory usage: Check if tile-based approach uses shared memory for intermediate results
  • Register pressure: Avoid excessive register usage that causes spilling
  • Warp divergence: Minimize branching within warps

Common Performance Anti-Patterns

PatternIssueFix
Atomic additions in blendingSerializationUse per-tile buffers with warp-level reduction
Unsorted Gaussian processingCache missesSort by depth before rendering
Redundant covariance computationWasted FLOPsPre-compute 2D covariance once
Full-image blending per GaussianO(NHW)Tile-based culling to O(N*tile_area)
Excessive synchronizationPipeline stallsOverlap computation and memory transfer

3. Training Pipeline

Adaptive Density Control (ADC)

  • Clone threshold: Verify gradient-based clone decision (grad threshold)
  • Split threshold: Verify position-based split decision (scale threshold)
  • Prune: Check opacity pruning threshold (typically α < 0.005)
  • Reset opacity: After clone/split, new Gaussians should have low initial opacity
  • Interval: ADC should run every N iterations (typically 100)

Loss Function

  • L1 loss: Standard pixel-wise L1 between rendered and ground truth
  • D-SSIM loss: Structural dissimilarity on patches (window size typically 11)
  • Lambda balance: Typical λ_DSSIM = 0.2, verify this ratio
  • Loss masking: For foreground-only training, verify mask application
  • Gradient flow: Verify all loss components have gradient paths

Training Schedule

  • Learning rate: Official 3DGS defaults (INRIA reference implementation): 0.00016 position, 0.0025 SH features, 0.05 opacity, 0.005 scaling, 0.001 rotation
  • Learning rate decay: Exponential decay at 0.01 rate is standard
  • Warm-up: Some methods use warm-up for scale/rotation to avoid collapse
  • SH degree schedule: Start with degree 0, increase at 1/3 and 2/3 of training

4. Known Bug Patterns

Loaded on demand — See Bug Patterns Catalog for the complete catalog of 108+ known bug patterns organized by domain (CUDA, SLAM, compression, hardware acceleration, deformable aggregation, PBR materials, etc.). The following summary lists pattern categories:

CategoryCountKey Patterns
Critical Bugs6Wrong sort axis, missing EWA, incorrect covariance reg
Performance Bugs4No tile culling, CPU sorting, excessive SH
Subtle Bugs6No near-plane clip, SH for background, float precision
SLAM-Specific4No static/dynamic sep, keyframe-only temporal
Feed-Forward3Pixel-aligned unprojection, view-dep size scaling
Compression & Mixed-Precision4Greedy merge, uniform bit-width, octree without prediction
Hardware & Cross-Domain5Vulkan compute, RL density control, GEMM order
Medical & Specialized8Spectral crosstalk, event camera, fluid constraints
4DGS Temporal & Streaming6Temporal partitioning, progressive streaming, harmonization
Feed
阅读完整来源 ↗