Research map / 3D vision / Face and shape
Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View Images
Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Shengping Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add refiner (ablation) | Pix2Vox-A · ShapeNet single-view (13 categories) | mean IoU: 0.636 -> 0.661 | Improved |
| add context-aware fusion instead of average fusion (ablation) | Pix2Vox-A · ShapeNet multi-view (20 views) | mean IoU: 0.695 -> 0.706 | Improved |
| add context-aware fusion instead of average fusion (ablation) | Pix2Vox-F · ShapeNet multi-view (2 views) | mean IoU: 0.653 -> 0.660 | Improved |
| add context-aware fusion instead of average fusion (ablation) | Pix2Vox-A · ShapeNet multi-view (1 view) | mean IoU: 0.661 -> 0.661 | No clear effect |
| use context-aware or average fusion instead of 3D conv LSTM fusion (ablation) | Pix2Vox · ShapeNet multi-view | mean IoU | Improved |
| replace recurrent fusion in LSM with context-aware fusion | LSM · ShapeNet test set | IoU: about 2% | Improved |
| use Pix2Vox-A instead of Pix2Vox-F (higher-dimensional feature maps) | Pix2Vox · ShapeNet single-view (13 categories) | mean IoU: 0.634 -> 0.661 | Improved |
| use Pix2Vox-A instead of 3D-R2N2 | 3D-R2N2 · ShapeNet single-view (13 categories) | mean IoU: 0.560 -> 0.661 | Improved |
| add more input views | Pix2Vox-A · ShapeNet multi-view | mean IoU: 0.661 -> 0.706 | Improved |
| add refiner, with more input views (ablation) | Pix2Vox-A · ShapeNet multi-view | mean IoU | Mixed |
Closest papers by meaning
- Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images (IJCV 2020 · similarity 0.98)
- Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation (IJCV 2020 · similarity 0.90)
- Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (CVPR 2018 · similarity 0.89)
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (ECCV 2016 · similarity 0.89)
- CoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image (ECCV 2020 · similarity 0.88)
- Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image (ECCV 2026 · similarity 0.88)
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.
