Research map / Video / Video segmentation and tracking
Bilateral Space Video Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use bilateral-space segmentation with quality-oriented settings | BVSQ · DAVIS | IoU: 0.64 -> 0.67 | Helped |
| Use bilateral-space segmentation with quality-oriented settings | BVSQ · JumpCut | error: 2.78 -> 2.72 | Helped |
| Use bilateral-space segmentation with quality-oriented settings | BVSQ · SegTrack | IoU: 0.81 -> 0.60 | Hurt |
| Use bilateral-space segmentation instead of SEA | 480p video segmentation · 480p | runtime per frame: 6s -> 0.37s | Helped |
| Use bilateral-space segmentation instead of SEA | 1080p video segmentation · 1080p | runtime per frame: 30s -> 1.5s | Helped |
| Add active-contour refinement (ablation) | BVSQ on JumpCut · JumpCut | error: 2.72 -> 2.45 | Helped |
| Use adjacent interpolation rather than nearest-neighbor interpolation (ablation) | Bilateral-space video segmentation · Video segmentation | segmentation quality | Helped |
| Use adjacent interpolation rather than multi-linear interpolation (ablation) | Bilateral-space video segmentation · Video segmentation | runtime | Helped |
| Increase the temporal grid size (ablation) | Bilateral-space video segmentation · Benchmarks with limited object motion | segmentation quality | No clear effect |
| Add optical-flow warping before splatting (ablation) | Bilateral-space video segmentation · Video segmentation | segmentation quality | Mixed |
| Use patches as appearance features (ablation) | Bilateral-space video segmentation · Video segmentation | segmentation quality | Helped |
| Increase pixel-graph neighborhood connectivity (ablation) | Pixel-level graph-cut segmentation · Video segmentation | error | Helped |
Closest papers by meaning
- Feature Space Optimization for Semantic Video Segmentation (CVPR 2016 · similarity 0.86)
- Deep Spatio-Temporal Random Fields for Efficient Video Segmentation (CVPR 2018 · similarity 0.85)
- GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.84)
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 2025 · similarity 0.83)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.83)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · similarity 0.83)
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.