SurgTAP-3D: A Large-Scale Cross-Surgery Video Dataset with Contact-Aware 3D Motion Tracking
cs.CV, cs.RO
Submitted: 2026-11-08
Updated: 2026-11-08
Project page: https://wrld.github.io/surgtap-3d
Terminology
Sources
- Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge
- SurgPose: a Dataset for Articulated Robotic Surgical Tool Pose Estimation and Tracking
- Surg$\Sigma$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence
- SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
- Visuomotor Grasping with World Models for Surgical Robots
- Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning
- OpenVLA: An Open-Source Vision-Language-Action Model
- ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
- WorldVLA: Towards Autoregressive Action World Model
- GigaBrain-0: A World Model-Powered Vision-Language-Action Model
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
- Stereo Correspondence and Reconstruction of Endoscopic Data Challenge
- DELTA: Dense Efficient Long-range 3D Tracking for any video
- TAPNext: Tracking Any Point (TAP) as Next Token Prediction
- TAPIP3D: Tracking Any Point in Persistent 3D Geometry
- EndoWave: 4D Gaussian Splatting with Rational Wavelet for Endoscopic Reconstruction
- Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues
- Grounding Image Matching in 3D with MASt3R
- Continuous 3D Perception Model with Persistent State
- EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs