← Latest papers
💻 computer science

DAC-Pose: Dual-Agent Collaborative Framework for Pose-Guided Human Generation

DAC-Pose introduces a novel dual-agent collaborative framework that combines a Prior Semantic Reasoning agent for deducing unseen regions and a Discrepancy-Aware Visual Encoding agent for modeling spatial deformations, thereby achieving high-fidelity, identity-consistent human generation under drastic viewpoint shifts.

Original authors: Haotian Yang, Zhile Yang, Huiyu Zhou, Xin Sun

Published 2026-08-06
📖 1 min read☕ Coffee break read

Original authors: Haotian Yang, Zhile Yang, Huiyu Zhou, Xin Sun

Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer

Drowning in papers in your field?

Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.

Try Digest →