Yiqun Ning

宁逸群 · Zeno Ning

I am a Research Associate in the Department of Computing at The Hong Kong Polytechnic University, working with Chenhang He. My research focuses on generative AI and image editing, with recent work on fit-aware virtual try-on and controllable garment-body editing.

Research

I am interested in controllable visual generation systems that understand user intent, image structure, and fine-grained editing constraints.

Generative AI

Building controllable generation pipelines with diffusion and flow-matching models.

Diffusion Flow Matching

Image Editing

Editing images with semantic control, spatial consistency, and faithful preservation of visual details.

Editing Control

Virtual Try-On

Modeling garment fit, body shape, and realistic try-on behavior across diverse subjects.

FitVTON Garments

News

Recent releases and updates.

Publications

A growing list of research projects and papers.

FitVTON teaser figure

FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control

A fit-aware virtual try-on framework that models garment-body size control and evaluates fitting fidelity with the FittingEffect3K benchmark and a fit-oriented VLM protocol.