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 · AI review on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add jaccen/Awesome-Gaussian-Skills --skill 3dgs-code-reviewerAbout this skill
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)andC = Σ c_i * α_i * T_iare correctly implemented - Early termination: Verify
T < εcutoff 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
| Pattern | Issue | Fix |
|---|---|---|
| Atomic additions in blending | Serialization | Use per-tile buffers with warp-level reduction |
| Unsorted Gaussian processing | Cache misses | Sort by depth before rendering |
| Redundant covariance computation | Wasted FLOPs | Pre-compute 2D covariance once |
| Full-image blending per Gaussian | O(NHW) | Tile-based culling to O(N*tile_area) |
| Excessive synchronization | Pipeline stalls | Overlap 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:
| Category | Count | Key Patterns |
|---|---|---|
| Critical Bugs | 6 | Wrong sort axis, missing EWA, incorrect covariance reg |
| Performance Bugs | 4 | No tile culling, CPU sorting, excessive SH |
| Subtle Bugs | 6 | No near-plane clip, SH for background, float precision |
| SLAM-Specific | 4 | No static/dynamic sep, keyframe-only temporal |
| Feed-Forward | 3 | Pixel-aligned unprojection, view-dep size scaling |
| Compression & Mixed-Precision | 4 | Greedy merge, uniform bit-width, octree without prediction |
| Hardware & Cross-Domain | 5 | Vulkan compute, RL density control, GEMM order |
| Medical & Specialized | 8 | Spectral crosstalk, event camera, fluid constraints |
| 4DGS Temporal & Streaming | 6 | Temporal partitioning, progressive streaming, harmonization |
| Feed |