Research map / 3D vision / Depth and stereo
Joint Multiview Segmentation and Localization of RGB-D Images Using Depth-Induced Silhouette Consistency
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 joint multiview segmentation and localization with depth-induced silhouette consistency instead of RGB-D alignment alone (ablation) | RGB-D object scanning · Tomcat and Musicbox | model reconstruction error | Helped |
| Jointly optimize silhouettes and camera poses with silhouette consistency | RGB-D object scanning · Tomcat, Musicbox, Donkey, Dragon, Chair, Horse, Plant, Gundam, Bag, Bag2 | segmentation error rate: Tomcat: 0.35 vs 0.35; Bag: 0.23 vs 0.20 | Mixed |
| Jointly optimize silhouettes and camera poses with silhouette consistency | RGB-D object scanning · Tomcat, Musicbox, Donkey, Dragon, Chair, Horse, Plant, Gundam, Bag, Bag2 | calibration ratio | Helped |
| Add depth-induced silhouette consistency to RGB-D alignment (ablation) | RGB-D object scanning · Tomcat and Musicbox | model reconstruction error | Helped |
| Propagate silhouette constraints across all views, not only neighboring views | Multiview segmentation and localization · RGB-D object scanning | pose accuracy | Helped |
Closest papers by meaning
- Consistency of Silhouettes and Their Duals (CVPR 2016 · similarity 0.84)
- Uncertainty-Driven 6D Pose Estimation of Objects and Scenes From a Single RGB Image (CVPR 2016 · similarity 0.84)
- DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation (ICLR 2024 · similarity 0.82)
- SAM2Object: Consolidating View Consistency via SAM2 for Zero-Shot 3D Instance Segmentation (CVPR 2025 · similarity 0.82)
- HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation (CVPR 2024 · similarity 0.82)
- Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images (CVPR 2025 · similarity 0.82)
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.