ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Peiming, Wang, Ziyi, Liu, Mengyuan, Liu, Hong, Chen, Chen
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916338580062208
author Li, Peiming
Wang, Ziyi
Liu, Mengyuan
Liu, Hong
Chen, Chen
author_facet Li, Peiming
Wang, Ziyi
Liu, Mengyuan
Liu, Hong
Chen, Chen
contents Grasp generation aims to create complex hand-object interactions with a specified object. While traditional approaches for hand generation have primarily focused on visibility and diversity under scene constraints, they tend to overlook the fine-grained hand-object interactions such as contacts, resulting in inaccurate and undesired grasps. To address these challenges, we propose a controllable grasp generation task and introduce ClickDiff, a controllable conditional generation model that leverages a fine-grained Semantic Contact Map (SCM). Particularly when synthesizing interactive grasps, the method enables the precise control of grasp synthesis through either user-specified or algorithmically predicted Semantic Contact Map. Specifically, to optimally utilize contact supervision constraints and to accurately model the complex physical structure of hands, we propose a Dual Generation Framework. Within this framework, the Semantic Conditional Module generates reasonable contact maps based on fine-grained contact information, while the Contact Conditional Module utilizes contact maps alongside object point clouds to generate realistic grasps. We evaluate the evaluation criteria applicable to controllable grasp generation. Both unimanual and bimanual generation experiments on GRAB and ARCTIC datasets verify the validity of our proposed method, demonstrating the efficacy and robustness of ClickDiff, even with previously unseen objects. Our code is available at https://github.com/adventurer-w/ClickDiff.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19370
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models
Li, Peiming
Wang, Ziyi
Liu, Mengyuan
Liu, Hong
Chen, Chen
Computer Vision and Pattern Recognition
Grasp generation aims to create complex hand-object interactions with a specified object. While traditional approaches for hand generation have primarily focused on visibility and diversity under scene constraints, they tend to overlook the fine-grained hand-object interactions such as contacts, resulting in inaccurate and undesired grasps. To address these challenges, we propose a controllable grasp generation task and introduce ClickDiff, a controllable conditional generation model that leverages a fine-grained Semantic Contact Map (SCM). Particularly when synthesizing interactive grasps, the method enables the precise control of grasp synthesis through either user-specified or algorithmically predicted Semantic Contact Map. Specifically, to optimally utilize contact supervision constraints and to accurately model the complex physical structure of hands, we propose a Dual Generation Framework. Within this framework, the Semantic Conditional Module generates reasonable contact maps based on fine-grained contact information, while the Contact Conditional Module utilizes contact maps alongside object point clouds to generate realistic grasps. We evaluate the evaluation criteria applicable to controllable grasp generation. Both unimanual and bimanual generation experiments on GRAB and ARCTIC datasets verify the validity of our proposed method, demonstrating the efficacy and robustness of ClickDiff, even with previously unseen objects. Our code is available at https://github.com/adventurer-w/ClickDiff.
title ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.19370