Research map / 3D vision / 3D generation
Semantically Coherent Co-Segmentation and Reconstruction of Dynamic Scenes
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 semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · Breakdance | IoU: 89.1 -> 93.2 | Helped |
| Use semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · HumanEva | IoU: 94.0 -> 95.6 | Helped |
| Use semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · Odzemok | IoU: 91.8 -> 94.5 | Helped |
| Use semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · Magician | IoU: 91.2 -> 93.0 | Helped |
| Use semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · Juggler | IoU: 93.3 -> 94.7 | Helped |
| Use semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · DogJump | IoU: 89.4 -> 92.6 | Helped |
| Use semantically coherent multi-view co-segmentation and reconstruction instead of TcMVS | Dynamic-scene segmentation · Handshake | IoU: 86.5 -> 91.5 | Helped |
| Use semantic tracklets and joint optimization instead of CRF-RNN | Single-view video segmentation · Giraffe | IoU: 69.7 -> 72.5 | Helped |
| Use semantic tracklets and joint optimization instead of SCV | Single-view video segmentation · Tiger | IoU: 70.9 -> 68.9 | Hurt |
| Use semantic tracklets and joint optimization instead of CRF-RNN | Single-view video segmentation · Person | IoU: 63.0 -> 66.4 | Helped |
| Use semantic tracklets and joint optimization instead of CRF-RNN | Single-view video segmentation · Dog | IoU: 77.1 -> 75.8 | Hurt |
| Add semantic-label information to the optimization (ablation) | Proposed single- and multi-view segmentation · Odzemok | segmentation accuracy | Helped |
Closest papers by meaning
- Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling (CVPR 2016 · similarity 0.87)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos (ICLR 2024 · similarity 0.86)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.86)
- Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation (CVPR 2024 · similarity 0.85)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.85)
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.