Research map / 3D vision / Gaussian splatting
SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Method
Wentao Yang, Fanzhen Kong, Zejian Kang, Xiangru Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add active set acceleration (SparseOIT-B vs SparseOIT-A) (ablation) | SparseOIT · Tanks & Temples | Training time (s): 559 -> 445 | Improved |
| add active set acceleration (SparseOIT-B vs SparseOIT-A) (ablation) | SparseOIT · DeepBlending | Training time (s): 355 -> 309 | Improved |
| add active set acceleration (SparseOIT-B vs SparseOIT-A) (ablation) | SparseOIT · Mip-NeRF 360 | Training time (s): 531 -> 408 | Improved |
| add active set acceleration (ablation) | SparseOIT · Mip-NeRF 360 | PSNR: 27.19 -> 27.21 | No clear effect |
| add active set acceleration (ablation) | SparseOIT · Tanks & Temples | PSNR: 23.63 -> 23.68 | No clear effect |
| use recursive per-splat backward instead of 3DGS per-pixel backward (ablation) | SparseOIT · DeepBlending playroom | Training time (s): 981 -> 396 | Improved |
| use recursive per-splat backward instead of Taming-3DGS per-splat backward (ablation) | SparseOIT · DeepBlending playroom | Training time (s): 415 -> 396 | Improved |
| use recursive per-splat backward instead of per-pixel backward (ablation) | SparseOIT · DeepBlending playroom | PSNR: 30.04 -> 29.93 | Hurt |
| adopt Taming-3DGS densification strategy (SparseOIT-C vs SparseOIT-B) (ablation) | SparseOIT · Mip-NeRF 360 | Training time (s) / PSNR: time 408 -> 191; PSNR 27.21 -> 26.98 | Mixed |
| use SparseOIT instead of SortFree | OIT-based 3DGS · Tanks & Temples | PSNR: 22.97 -> 23.68 | Improved |
| use SparseOIT instead of SortFree | OIT-based 3DGS · Mip-NeRF 360 | PSNR: 27.33 -> 27.21 | Hurt |
Closest papers by meaning
- Fast and Compact 3D Gaussian Splatting with Polarized Opacity Prior (ECCV 2026 · similarity 0.91)
- Plug-and-Play Optimization for 3D Gaussian Splatting Compression: Distribution Regularization, Probabilistic Pruning and Detail Compensation (AAAI 2026 · similarity 0.91)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.90)
- Sort-free Gaussian Splatting via Weighted Sum Rendering (ICLR 2025 · similarity 0.90)
- Volumetrically Consistent 3D Gaussian Rasterization (CVPR 2025 · similarity 0.89)
- DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
