# AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild

arXiv: https://arxiv.org/abs/2407.18034 · HTML: https://mlsanity.com/paper/2407.18034/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 51 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [MediaPipe Hands: On-device Real-time Hand Tracking](https://mlsanity.com/paper/2006.10214/) (2020)
- [GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB](https://mlsanity.com/paper/1712.01057/) (2017)
- [Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation](https://mlsanity.com/paper/2104.14639/) (2021)
- [Capturing Hands in Action using Discriminative Salient Points and Physics Simulation](https://mlsanity.com/paper/1506.02178/) (2015)
- [Affordance Diffusion: Synthesizing Hand-Object Interactions](https://mlsanity.com/paper/2303.12538/) (2023)
- [Interacting Attention Graph for Single Image Two-Hand Reconstruction](https://mlsanity.com/paper/2203.09364/) (2022)
- [AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation](https://mlsanity.com/paper/2304.12301/) (2023)
- [HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting](https://mlsanity.com/paper/2311.17957/) (2023)
- [HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances](https://mlsanity.com/paper/2403.01693/) (2024)
- [3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal](https://mlsanity.com/paper/2207.11061/) (2022)
- [Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild](https://mlsanity.com/paper/2303.13652/) (2023)

## Built on by (most cited first, 10 of 10)

- [Mask2IV: Interaction-Centric Video Generation via Mask Trajectories](https://mlsanity.com/paper/2510.03135/) (2025)
- [EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations](https://mlsanity.com/paper/2506.17896/) (2025)
- [FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation](https://mlsanity.com/paper/2412.02690/) (2024)
- [UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation](https://mlsanity.com/paper/2503.13303/) (2025)
- [Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves](https://mlsanity.com/paper/2603.20850/) (2026)
- [Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models](https://mlsanity.com/paper/2506.17707/) (2025)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [3D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Model](https://mlsanity.com/paper/2506.12680/) (2025)
- [SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment](https://mlsanity.com/paper/2603.00443/) (2026)
- [Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance Heritage](https://mlsanity.com/paper/2609.03415/) (2026)

## Abstract (arXiv)

Recently, there has been a significant amount of research conducted on 3D hand reconstruction to use various forms of human-computer interaction. However, 3D hand reconstruction in the wild is challenging due to extreme lack of in-the-wild 3D hand datasets. Especially, when hands are in complex pose such as interacting hands, the problems like appearance similarity, self-handed occclusion and depth ambiguity make it more difficult. To overcome these issues, we propose AttentionHand, a novel method for text-driven controllable hand image generation. Since AttentionHand can generate various and numerous in-the-wild hand images well-aligned with 3D hand label, we can acquire a new 3D hand dataset, and can relieve the domain gap between indoor and outdoor scenes. Our method needs easy-to-use four modalities (i.e, an RGB image, a hand mesh image from 3D label, a bounding box, and a text prompt). These modalities are embedded into the latent space by the encoding phase. Then, through the text attention stage, hand-related tokens from the given text prompt are attended to highlight hand-related regions of the latent embedding. After the highlighted embedding is fed to the visual attention stage, hand-related regions in the embedding are attended by conditioning global and local hand mesh images with the diffusion-based pipeline. In the decoding phase, the final feature is decoded to new hand images, which are well-aligned with the given hand mesh image and text prompt. As a result, AttentionHand achieved state-of-the-art among text-to-hand image generation models, and the performance of 3D hand mesh reconstruction was improved by additionally training with hand images generated by AttentionHand.