Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Ma, Liqian"'
Autor:
Jiang, Taoran, Ma, Liqian, Guan, Yixuan, Meng, Jiaojiao, Chen, Weihang, Zeng, Zecui, Li, Lusong, Wu, Dan, Xu, Jing, Chen, Rui
Articulated object manipulation is ubiquitous in daily life. In this paper, we present DexSim2Real$^{2}$, a novel robot learning framework for goal-conditioned articulated object manipulation using both two-finger grippers and multi-finger dexterous
Externí odkaz:
http://arxiv.org/abs/2409.08750
The requirements for real-world manipulation tasks are diverse and often conflicting; some tasks require precise motion while others require force compliance; some tasks require avoidance of certain regions, while others require convergence to certai
Externí odkaz:
http://arxiv.org/abs/2405.11380
Recent advances in text-to-image models have opened new frontiers in human-centric generation. However, these models cannot be directly employed to generate images with consistent newly coined identities. In this work, we propose CharacterFactory, a
Externí odkaz:
http://arxiv.org/abs/2404.15677
Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure stable identi
Externí odkaz:
http://arxiv.org/abs/2401.15975
Image inpainting aims to fill in the missing pixels with visually coherent and semantically plausible content. Despite the great progress brought from deep generative models, this task still suffers from i. the difficulties in large-scale realistic d
Externí odkaz:
http://arxiv.org/abs/2310.02848
In this paper, we define and study a new Cloth2Body problem which has a goal of generating 3D human body meshes from a 2D clothing image. Unlike the existing human mesh recovery problem, Cloth2Body needs to address new and emerging challenges raised
Externí odkaz:
http://arxiv.org/abs/2309.16189
Safety in dynamic systems with prevalent uncertainties is crucial. Current robust safe controllers, designed primarily for uni-modal uncertainties, may be either overly conservative or unsafe when handling multi-modal uncertainties. To address the pr
Externí odkaz:
http://arxiv.org/abs/2309.16830
In this work, we focus on synthesizing high-fidelity novel view images for arbitrary human performers, given a set of sparse multi-view images. It is a challenging task due to the large variation among articulated body poses and heavy self-occlusions
Externí odkaz:
http://arxiv.org/abs/2303.13777
Accurately manipulating articulated objects is a challenging yet important task for real robot applications. In this paper, we present a novel framework called Sim2Real$^2$ to enable the robot to manipulate an unseen articulated object to the desired
Externí odkaz:
http://arxiv.org/abs/2302.10693
In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the implicit r
Externí odkaz:
http://arxiv.org/abs/2212.02765