DAC-Pose is proposed, a novel agent-driven multimodal framework that reformulates single-view human generation as a collaborative dual-agent system that excels in preserving texture alignment and identity consistency under drastic viewpoint changes.
Hao-Tian Yang, Zhi-Le Yang, Hui-Yu Zhou et al.· 1 citation
Qualitative results show that the proposed HiPA-Gen framework produces clearer limb boundaries, more reliable spatial ordering, and more consistent clothing textures in challenging pose interaction scenarios.
Juncheng Zhu, Hao-Tian Yang, Mubai Li et al.· Electronics· 0 citations
Compared with the reproduced UniDexGrasp-T baseline under the same object split and evaluation protocol, DexGraspDiffuser improves the three-split average success rate by 3.3 percentage points and reduces the average mean position error by 0.53 cm, indicating that target-coupled grasp and action diffusion contribute to...
Juncheng Zhu, Haotian Yang, Zhile Yang et al.· Biomimetics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.