Research map / Vision-language and multimodal / Human and embodied modeling
Connecting Look and Feel: Associating the Visual and Tactile Properties of Physical Materials
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 |
|---|---|---|---|
| train jointly on depth and GelSight rather than depth alone | Depth-to-depth matching · Seen and novel fabrics | top-1 precision: 0.482 -> 0.608; 0.554 -> 0.606 | Helped |
| use three GelSight presses instead of one (ablation) | Multi-input Net · Fabric test set, Depth2Gel | top-1 precision: 0.4318 -> 0.4576 | Helped |
| add human-labeled cluster-classification supervision (ablation) | Cross-modal Net · Fabric test set, Depth2Gel | top-1 precision: 0.4292 -> 0.4318 | Helped |
| press GelSight on a fold rather than flat fabric (ablation) | Cross-modal Net · Fabric test set, Depth2Gel | top-1 precision: 0.3063 -> 0.4292 | Helped |
| apply color-image augmentation (ablation) | Cross-modal Net and Multi-input Net · Color-involved matching | top-1 precision: 0.3954 -> 0.4359; 0.4303 -> 0.4937 | Helped |
| apply color-image augmentation (ablation) | Cross-modal Net and Multi-input Net · Depth-to-depth and GelSight-to-depth matching | top-1 precision | No clear effect |
| add noise or randomly crop depth and GelSight inputs (ablation) | Cross-modal Net · Fabric matching | matching precision | No clear effect |
| use three GelSight presses instead of one (ablation) | Multi-input Net · Fabric test set, Gel2Gel | top-1 precision: 0.8090 -> 0.9351 | Helped |
Closest papers by meaning
- GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation (CVPR 2025 · similarity 0.85)
- NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory (NeurIPS 2024 · similarity 0.85)
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors (ICLR 2025 · similarity 0.85)
- TexTile: A Differentiable Metric for Texture Tileability (CVPR 2024 · similarity 0.85)
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.85)
- Binding Touch to Everything: Learning Unified Multimodal Tactile Representations (CVPR 2024 · 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.