Research map / 3D vision / Depth and stereo
Multi-View 3D Reconstruction With Transformers
Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, Rabab Ward
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 view-divergence enhancing function (DiView) (ablation) | VolT · ShapeNet (24 views) | IoU: 0.714 -> 0.738 | Improved |
| add view-divergence enhancing function (DiView) (ablation) | VolT · ShapeNet (24 views) | F-Score@1%: 0.468 -> 0.497 | Improved |
| add view-divergence enhancing function (DiView) (ablation) | VolT · ShapeNet (4 views) | IoU: 0.605 -> 0.609 | No clear effect |
| add view-divergence enhancing function (DiView) (ablation) | VolT · ShapeNet (8 views) | IoU: 0.681 -> 0.698 | Improved |
| use stronger pretrained 2D-CNN features for view embeddings | VolT · ShapeNet (24 views) | IoU: 0.714 -> 0.716 | Improved |
| use stronger pretrained 2D-CNN features for view embeddings | VolT · ShapeNet (4 views) | IoU: 0.605 -> 0.695 | Improved |
| increase number of input views from 8 to 24 | EVolT · ShapeNet | IoU: increases by 0.04 | Improved |
| compare EVolT with Pix2Vox++/A with few views | EVolT · ShapeNet (4 views) | IoU: 0.609 vs 0.708 | Hurt |
| add view-divergence enhancing function (DiView) (ablation) | VolT · ShapeNet | view-attention divergence D | Improved |
Closest papers by meaning
- Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding (ECCV 2026 · similarity 0.89)
- Monocular Scene Reconstruction with 3D SDF Transformers (ICLR 2023 · similarity 0.89)
- Volumetric and Multi-View CNNs for Object Classification on 3D Data (CVPR 2016 · similarity 0.89)
- Long-Range Grouping Transformer for Multi-View 3D Reconstruction (ICCV 2023 · similarity 0.88)
- Understanding Multi-View Transformers (NeurIPS 2026 · similarity 0.87)
- VGGT: Visual Geometry Grounded Transformer (CVPR 2025 · 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.
