Research map / 3D vision / Face and shape
Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction
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 |
|---|---|---|---|
| Replace voxel prediction with multi-surface prediction | Viewer-centered shape prediction · SHREC'12 NovelClass | Surface Distance: 0.0950 -> 0.0759 | Helped |
| Replace voxel prediction with multi-surface prediction | Viewer-centered shape prediction · SHREC'12 NovelClass | Voxel IoU: 0.4569 -> 0.4914 | Helped |
| Replace voxel prediction with multi-surface prediction | Viewer-centered shape prediction · SHREC'12 NovelModel | Surface Distance: 0.0619 -> 0.0622 | No clear effect |
| Replace voxel prediction with multi-surface prediction | Viewer-centered shape prediction · SHREC'12 NovelView | Surface Distance: 0.0512 -> 0.0494 | Helped |
| Use viewer-centered instead of object-centered coordinates (ablation) | Voxel network · SHREC'12 NovelView | Voxel IoU: 0.902 -> 0.714 | Hurt |
| Use viewer-centered instead of object-centered coordinates (ablation) | Voxel network · SHREC'12 NovelModel | Voxel IoU: 0.474 -> 0.570 | Helped |
| Use viewer-centered instead of object-centered coordinates (ablation) | Voxel network · SHREC'12 NovelClass | Voxel IoU: 0.309 -> 0.517 | Helped |
| Use viewer-centered instead of object-centered coordinates (ablation) | 6-view multi-surface network · SHREC'12 NovelView | Silhouette IoU: 0.921 -> 0.807 | Hurt |
| Use viewer-centered instead of object-centered coordinates (ablation) | 6-view multi-surface network · SHREC'12 NovelModel | Silhouette IoU: 0.586 -> 0.706 | Helped |
| Use viewer-centered instead of object-centered coordinates (ablation) | 6-view multi-surface network · SHREC'12 NovelClass | Silhouette IoU: 0.416 -> 0.670 | Helped |
| Use viewer-centered instead of object-centered coordinates (ablation) | 6-view multi-surface network · SHREC'12 NovelModel | Depth error: 0.035 -> 0.016 | Helped |
| Use viewer-centered instead of object-centered coordinates (ablation) | 6-view multi-surface network · SHREC'12 NovelClass | Depth error: 0.0503 -> 0.0207 | Helped |
Closest papers by meaning
- Structured Prediction of Unobserved Voxels From a Single Depth Image (CVPR 2016 · similarity 0.91)
- Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks (CVPR 2017 · similarity 0.89)
- Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction (CVPR 2020 · similarity 0.89)
- Shape Unicode: A Unified Shape Representation (CVPR 2019 · similarity 0.89)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.87)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.87)
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.