# TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions

arXiv: https://arxiv.org/abs/2510.14874 · HTML: https://mlsanity.com/paper/2510.14874/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 78 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 30 of 64)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://mlsanity.com/paper/2212.08751/) (2022)
- [InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models](https://mlsanity.com/paper/2404.07191/) (2024)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines](https://mlsanity.com/paper/2005.00343/) (2020)
- [ContactPose: A Dataset of Grasps with Object Contact and Hand Pose](https://mlsanity.com/paper/2007.09545/) (2020)
- [Grasping Field: Learning Implicit Representations for Human Grasps](https://mlsanity.com/paper/2008.04451/) (2020)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [Reconstructing Hand-Object Interactions in the Wild](https://mlsanity.com/paper/2012.09856/) (2020)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)

## Built on by (most cited first, 8 of 8)

- [GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting](https://mlsanity.com/paper/2603.18912/) (2026)
- [Gloria: Consistent Character Video Generation via Content Anchors](https://mlsanity.com/paper/2603.29931/) (2026)
- [Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation](https://mlsanity.com/paper/2606.30598/) (2026)
- [EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning](https://mlsanity.com/paper/2603.09731/) (2026)
- [End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction](https://mlsanity.com/paper/2603.14435/) (2026)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [LogiShot: Logically Coherent Cross-Shot Video Generation](https://mlsanity.com/paper/2608.08820/) (2026)
- [PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph](https://mlsanity.com/paper/2608.01905/) (2026)

## Abstract (arXiv)

Hand-object interaction (HOI) is fundamental for humans to express intent. Existing HOI generation research is predominantly confined to fixed grasping patterns, where control is tied to physical priors such as force closure or generic intent instructions, even when expressed through elaborate language. Such an overly general conditioning imposes a strong inductive bias for stable grasps, thus failing to capture the diversity of daily HOI. To address these limitations, we introduce Free-Form HOI Generation, which aims to generate controllable, diverse, and physically plausible HOI conditioned on fine-grained intent, extending HOI from grasping to free-form interactions, like pushing, poking, and rotating. To support this task, we construct WildO2, an in-the-wild diverse 3D HOI dataset, which includes diverse HOI derived from internet videos. Specifically, it contains 4.4k unique interactions across 92 intents and 610 object categories, each with detailed semantic annotations. Building on this dataset, we propose TOUCH, a three-stage framework centered on a multi-level diffusion model that facilitates fine-grained semantic control to generate versatile hand poses beyond grasping priors. This process leverages explicit contact modeling for conditioning and is subsequently refined with contact consistency and physical constraints to ensure realism. Comprehensive experiments demonstrate our method's ability to generate controllable, diverse, and physically plausible hand interactions representative of daily activities. The project page is hrefhttps://guangyid.github.io/hoi123touchhere.