FastGrasp: Efficient Grasp Synthesis with Diffusion

TL;DR

FastGrasp introduces a diffusion-model-based method for rapid, diverse, and physically plausible human hand grasp synthesis, significantly outperforming prior two-stage approaches in speed and quality.

Contribution

The paper presents a novel one-stage diffusion model for hand-object grasp synthesis, improving efficiency and diversity over traditional two-stage methods.

Findings

Faster inference compared to state-of-the-art methods

Higher diversity in generated hand poses

Superior pose quality demonstrated through extensive experiments

Abstract

Effectively modeling the interaction between human hands and objects is challenging due to the complex physical constraints and the requirement for high generation efficiency in applications. Prior approaches often employ computationally intensive two-stage approaches, which first generate an intermediate representation, such as contact maps, followed by an iterative optimization procedure that updates hand meshes to capture the hand-object relation. However, due to the high computation complexity during the optimization stage, such strategies often suffer from low efficiency in inference. To address this limitation, this work introduces a novel diffusion-model-based approach that generates the grasping pose in a one-stage manner. This allows us to significantly improve generation speed and the diversity of generated hand poses. In particular, we develop a Latent Diffusion Model with an Adaptation Module for object-conditioned hand pose generation and a contact-aware loss to enforce the physical constraints between hands and objects. Extensive experiments demonstrate that our method achieves faster inference, higher diversity, and superior pose quality than state-of-the-art approaches. Code is available at \href{https://github.com/wuxiaofei01/FastGrasp}{https://github.com/wuxiaofei01/FastGrasp.}