Research map / Video / Video segmentation and tracking
Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and Dataset
Qifan Liang, Junlin Li, Zhen Han, Xihao Wang, Zhongyuan Wang, Bin Mei
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 |
|---|---|---|---|
| train on STSVD instead of PSv2rs (ablation) | STANet baseline · STSVD | PSNR: 29.2978 -> 31.1898 | Improved |
| train on STSVD instead of PSv2rs (ablation) | STANet baseline · Vivo | PSNR: 22.9287 -> 23.0744 | Improved |
| add Semantic Soft Segmentation Module (S3M) (ablation) | STANet baseline · STSVD | PSNR: 31.1898 -> 31.8980 | Improved |
| add S3M (ablation) | STANet baseline · Vivo | SSIM: 0.8634 -> 0.8755 | Improved |
| add Coarse-to-Fine Disentanglement Module (C2FDM) (ablation) | STANet with S3M · STSVD | PSNR: 31.8980 -> 32.7462 | Improved |
| add C2FDM (ablation) | STANet with S3M · STSVD | LPIPS: 0.0545 -> 0.0491 | Improved |
| add Smoke High-frequency Wing Loss (SHWL) (ablation) | STANet with S3M and C2FDM · STSVD | PSNR: 32.7462 -> 33.0871 | Improved |
| add SHWL (ablation) | STANet with S3M and C2FDM · Vivo | PSNR: 23.3514 -> 23.5024 | Improved |
| add smokeless video reconstruction sub-network (SVRS) (ablation) | STANet M5 · STSVD | PSNR: 33.0871 -> 33.5345 | Improved |
| add SVRS (ablation) | STANet M5 · STSVD-R | MUSIQ: 39.8560 -> 40.2063 | Improved |
| add SVRS (ablation) | STANet M5 · Vivo | PSNR: 23.5024 -> 23.8427 | Improved |
| use STANet desmoked input instead of SelfSVD | polyp detection · CVC-ColonDB | DSC: 0.6932 -> 0.7138 | Improved |
Closest papers by meaning
- FoSp: Focus and Separation Network for Early Smoke Segmentation (AAAI 2024 · similarity 0.83)
- Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark (AAAI 2026 · similarity 0.81)
- SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark (CVPR 2026 · similarity 0.81)
- Guided Real Image Dehazing Using YCbCr Color Space (AAAI 2025 · similarity 0.80)
- MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments (CVPR 2025 · similarity 0.80)
- CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools (CVPR 2025 · similarity 0.80)
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.
