PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation
cs.CV
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/VDIGPKU/PhysTacGen
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors
- ViTacFormer: Learning Cross-Modal Representation for Visuo-Tactile Dexterous Manipulation
- Sparsh: Self-supervised touch representations for vision-based tactile sensing
- Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Features
- Digitizing Touch with an Artificial Multimodal Fingertip
- V-HOP: Visuo-Haptic 6D Object Pose Tracking
- DINOv2: Learning Robust Visual Features without Supervision
- One-Step Image Translation with Text-to-Image Models
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
- Octopi: Object Property Reasoning with Large Tactile-Language Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models