April 25, 2024, 7:45 p.m. | Linzi Qu, Jiaxiang Shang, Hui Ye, Xiaoguang Han, Hongbo Fu

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.15889v1 Announce Type: new
Abstract: Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacking explicit geometry and appearance control of body and garment. Sketching offers such editing ability and has been adopted in various sketch-based face generation and editing solutions. However, directly adapting sketch-based face generation to full-body generation often fails to produce high-fidelity and diverse results due to the high …

abstract arxiv control cs.cv cs.gr editing geometry human image image generation solutions text type

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US