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

TL;DR

AttentionHand is a novel text-driven method for controllable hand image generation that enhances 3D hand reconstruction in the wild by generating diverse, well-aligned hand images from multiple modalities, improving dataset diversity and model performance.

Contribution

It introduces a new diffusion-based framework that uses multiple modalities and attention mechanisms for controllable hand image synthesis, advancing 3D hand reconstruction in complex scenarios.

Findings

Achieved state-of-the-art results in text-to-hand image generation.

Improved 3D hand mesh reconstruction accuracy.

Generated diverse in-the-wild hand images aligned with 3D labels.

Abstract

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.