# Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions

arXiv: https://arxiv.org/abs/2505.05517 · HTML: https://mlsanity.com/paper/2505.05517/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 62 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 30 of 48)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains](https://mlsanity.com/paper/2212.08333/) (2022)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System](https://mlsanity.com/paper/2307.04577/) (2023)
- [ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging](https://mlsanity.com/paper/1904.06830/) (2019)
- [Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation](https://mlsanity.com/paper/2403.03949/) (2024)
- [ContactOpt: Optimizing Contact to Improve Grasps](https://mlsanity.com/paper/2104.07267/) (2021)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://mlsanity.com/paper/1706.07036/) (2017)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data](https://mlsanity.com/paper/2505.03233/) (2025)
- [Affordance Diffusion: Synthesizing Hand-Object Interactions](https://mlsanity.com/paper/2303.12538/) (2023)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [VideoDex: Learning Dexterity from Internet Videos](https://mlsanity.com/paper/2212.04498/) (2022)
- [What's in your hands? 3D Reconstruction of Generic Objects in Hands](https://mlsanity.com/paper/2204.07153/) (2022)
- [ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact](https://mlsanity.com/paper/1904.03754/) (2019)
- [DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation](https://mlsanity.com/paper/2211.09423/) (2022)
- [Describe Anything: Detailed Localized Image and Video Captioning](https://mlsanity.com/paper/2504.16072/) (2025)
- [OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion](https://mlsanity.com/paper/2403.19417/) (2024)
- [LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning](https://mlsanity.com/paper/2309.06440/) (2023)

## Built on by (most cited first, 11 of 11)

- [Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations](https://mlsanity.com/paper/2511.16661/) (2025)
- [Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction](https://mlsanity.com/paper/2602.09013/) (2026)
- [DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos](https://mlsanity.com/paper/2510.08475/) (2025)
- [TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions](https://mlsanity.com/paper/2510.14874/) (2025)
- [ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos](https://mlsanity.com/paper/2602.06226/) (2026)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [Human Universal Grasping](https://mlsanity.com/paper/2606.17054/) (2026)
- [D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping](https://mlsanity.com/paper/2603.01151/) (2026)
- [Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration](https://mlsanity.com/paper/2601.05243/) (2026)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis](https://mlsanity.com/paper/2609.16319/) (2026)

## Abstract (arXiv)

Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. Prior work largely focuses on power grasps, which only involve holding an object, or relies on in-domain demonstrations for specific objects. We propose leveraging human grasp information extracted from web images, which capture natural and functional hand-object interactions (HOI). Using a pretrained 3D reconstruction model, we recover 3D human HOI meshes from RGB images. To train on these noisy HOI data, we propose to use: (1) an interaction-centric model to learn the functional interaction pattern between hand and object, and (2) geometry-based filtering to remove the infeasible grasps and physical simulation to retain grasps who can resist disturbance. In IssacGym simulation, our model trained on reconstructed HOI grasps achieves a 75.8% success rate on objects from the web dataset and generalizes to unseen objects, outperforming baseline methods in both grasp success and functional quality. In real-world experiments with the LEAP hand and Inspire hand, it attains a 77.5% success rate across 12 objects, including challenging ones such as a syringe, spray bottle, knife, and tongs. Project website is at: https://web2grasp.github.io/.