Research map / 3D vision / Face and shape
3D Shape Reconstruction from Vision and Touch
Edward Smith, Roberto Calandra, Adriana Romero, Georgia Gkioxari, David Meger, Jitendra Malik, Michal Drozdzal
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 |
|---|---|---|---|
| replace sphere-based fusion with chart-based fusion (ablation) | vision+touch model · validation, unoccluded vision | avg Chamfer distance: 0.813 -> 0.751 | Improved |
| replace sphere-based fusion with chart-based fusion (ablation) | vision+touch model · validation, occluded vision | avg Chamfer distance: 0.992 -> 0.876 | Improved |
| replace sphere-based with chart-based (ablation) | vision-only model · validation, occluded vision | avg Chamfer distance: 1.072 -> 1.020 | Improved |
| add hard copying of touch charts to final prediction (ablation) | chart-based model · validation, unoccluded vision | avg Chamfer distance: 0.756 -> 0.751 | Improved |
| add hard copying of touch charts to final prediction (ablation) | chart-based model · validation, occluded vision | avg Chamfer distance: 0.919 -> 0.876 | Improved |
| add communication between touch and vision charts (ablation) | chart-based model · validation, unoccluded vision | avg Chamfer distance: 0.788 -> 0.751 | Improved |
| add communication between touch and vision charts (ablation) | chart-based model · validation, occluded vision | avg Chamfer distance: 1.014 -> 0.876 | Improved |
| add touch to occluded vision (ablation) | chart-based model · validation, occluded vision | avg Chamfer distance: 1.020 -> 0.876 | Improved |
| add touch to unoccluded vision (ablation) | chart-based model · validation, unoccluded vision | avg Chamfer distance: 0.797 -> 0.751 | Improved |
| remove vision (touch only) (ablation) | chart-based model · test set | global Chamfer distance: 1.074 -> 3.050 | Hurt |
| increase number of grasps from 1 to 5 (ablation) | unoccluded vision + touch · multi-grasp | Chamfer distance: 0.804 -> 0.654 | Improved |
| increase number of grasps from 1 to 5 (ablation) | touch only · multi-grasp | Chamfer distance: 3.05 -> 1.237 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Pixel2Mesh — Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (ECCV 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Active 3D Shape Reconstruction from Vision and Touch (NeurIPS 2021 · similarity 0.90)
- TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touches (ECCV 2026 · similarity 0.88)
- Touch2Shape: Touch-Conditioned 3D Diffusion for Shape Exploration and Reconstruction (CVPR 2025 · similarity 0.87)
- Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation (NeurIPS 2024 · similarity 0.84)
- Tactile-Augmented Radiance Fields (CVPR 2024 · similarity 0.84)
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors (ICLR 2025 · similarity 0.84)
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.
