Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

• URL: http://arxiv.org/abs/2606.12069v1
• Date: Wed, 10 Jun 2026 13:33:42 GMT
• Title: Tac-DINO: Learning Vision-Tactile Features with Patch Alignment
• Abstract summary: We build a data collection system to acquire a large-scale tactile dataset, with over 20 K tactile contacts from 505 real-world objects.<n>We then design a Vis-Tac Holographic Matching Benchmark to evaluate vision-tactile local-to-global alignment ability.<n>Then we propose Vision-Tactile Patch Alignment (VTPA) methods for vision-tactile representation learning.
• Score: 47.4807111947232
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile signals correspond to local object contact, while research into scale alignment and holographic matching remains limited and proper datasets and benchmarks also lack. To bridge this gap, we first construct a data collection system to acquire a large-scale tactile dataset, with over 20 K tactile contacts from 505 real-world objects. Building on this dataset, we design a Vis-Tac Holographic Matching Benchmark to evaluate vision-tactile local-to-global alignment ability. Then we propose Vision-Tactile Patch Alignment (VTPA) methods for vision-tactile representation learning. Experiments demonstrate that these exceed the performance of methods without alignment and align with whole-object images.

Related papers

• VTLoc: Learning-based Tactile Contact Localization in Visual Point Clouds [16.86791443254927]
  VTLoc is a visual-tactile framework that localizes contact points from tactile readings using a 3D point cloud as visual input.<n> evaluated on a new benchmark of 100 real-world objects.
  arXiv  Detail & Related papers  (2026-07-17T17:27:08Z)
• TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation [50.608989079323784]
  We propose TouchThinker, a tactile-language framework that scales tactile commonsense reasoning to the open world from both data and representation perspectives.<n>First, we construct TouchThinker-1M, a million-scale, multi-source tactile reasoning dataset covering textbf415 objects, textbf8 scenarios, and textbf7 sensor types.<n>Then, we propose action-aware modeling mechanism to improve tactile representation efficiency and enable efficient reasoning.
  arXiv  Detail & Related papers  (2026-06-10T03:58:32Z)
• Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions [42.26043073031702]
  We address the problem of tactile localization, where the goal is to identify image regions that share the same material properties as a tactile input.<n>Existing visuo-tactile methods rely on global alignment and thus fail to capture the fine-grained local correspondences required for this task.<n>We propose a model that learns local visuo-tactile alignment via dense cross-modal feature interactions, producing tactile saliency maps for touch-conditioned material segmentation.
  arXiv  Detail & Related papers  (2026-04-13T14:57:52Z)
• OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation [57.133721026727706]
  We present textbfOmniViTac, a large-scale visuo-tactile-action dataset comprising $21,000+$ trajectories across $86$ tasks and $100+$ objects.<n>We propose textbf OmniVTA, a world-model-based visuo-tactile manipulation framework that integrates four tightly coupled modules.
  arXiv  Detail & Related papers  (2026-03-19T17:52:42Z)
• Semantic-Contact Fields for Category-Level Generalizable Tactile Tool Manipulation [82.63833405368159]
  Generalizing tool manipulation requires both semantic planning and precise physical control.<n>We propose Semantic-Contact Fields (SCFields), a unified 3D representation fusing visual semantics with dense contact estimates.<n> Experiments on scraping, crayon drawing, and peeling demonstrate robust category-level generalization.
  arXiv  Detail & Related papers  (2026-02-14T16:05:08Z)
• UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking [47.900334665380115]
  We propose UniVTAC, a simulation-based visuo-tactile data platform.<n>We introduce the UniVTAC encoder, a visuo-tactile encoder trained on large-scale simulation-synthesized data.<n>We present the UniVTAC Benchmark, which consists of eight representative visuo-tactile manipulation tasks.
  arXiv  Detail & Related papers  (2026-02-10T18:57:00Z)
• OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction [93.88239833545623]
  We present OpenTouch, the first in-the-wild egocentric full-hand tactile dataset.<n>We show that tactile signals provide a compact yet powerful cue for grasp understanding.<n>We aim to advance multimodal egocentric perception, embodied learning, and contact-rich robotic manipulation.
  arXiv  Detail & Related papers  (2025-12-18T18:18:17Z)
• Tactile MNIST: Benchmarking Active Tactile Perception [19.93022179513013]
  We introduce the Tactile MNIST Benchmark Suite, an open-source, Gymnasium-compatible benchmark for tactile perception tasks.<n>Our benchmark suite offers diverse simulation scenarios, from simple toy environments all the way to complex tactile perception tasks using vision-based tactile sensors.<n>We also offer a comprehensive dataset comprising 13,500 synthetic 3D MNIST digit models and 153,600 real-world tactile samples collected from 600 3D printed digits.
  arXiv  Detail & Related papers  (2025-06-03T14:42:16Z)
• Visual-Tactile Sensing for In-Hand Object Reconstruction [38.42487660352112]
  We propose a visual-tactile in-hand object reconstruction framework textbfVTacO, and extend it to textbfVTacOH for hand-object reconstruction. A simulation environment, VT-Sim, supports generating hand-object interaction for both rigid and deformable objects.
  arXiv  Detail & Related papers  (2023-03-25T15:16:31Z)
• Touch and Go: Learning from Human-Collected Vision and Touch [16.139106833276]
  We propose a dataset with paired visual and tactile data called Touch and Go. Human data collectors probe objects in natural environments using tactile sensors. Our dataset spans a large number of "in the wild" objects and scenes.
  arXiv  Detail & Related papers  (2022-11-22T18:59:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.