Research map / Video / Video segmentation and tracking
Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds
Read the paperCheck 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 content-sensitive tessellation on the video manifold instead of TSP | CSS · BuffaloXiph | runtime: 5× to 10× faster | Helped |
| Use content-sensitive tessellation on the video manifold instead of TSP | CSS · BuffaloXiph | peak memory: 22× smaller | Helped |
| Use streaming processing for long videos | streamCSS · BuffaloXiph | peak memory: 22× smaller | Helped |
| Adapt supervoxel sizes to video content density | CSS · BuffaloXiph | compactness | Helped |
| Compute a uniform tessellation on the combined color and spatiotemporal video manifold | CSS · BuffaloXiph | 3D segmentation accuracy (SA3D) | Helped |
| Compute a uniform tessellation on the combined color and spatiotemporal video manifold | CSS · BuffaloXiph | 3D under-segmentation error (UE3D) | Helped |
Closest papers by meaning
- CoDeF: Content Deformation Fields for Temporally Consistent Video Processing (CVPR 2024 · similarity 0.83)
- DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization (ICLR 2024 · similarity 0.83)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.83)
- Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels (NeurIPS 2024 · similarity 0.83)
- Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors (NeurIPS 2026 · similarity 0.83)
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction (NeurIPS 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.