Ziying Zhang — accepted AI-conference papers

2026

LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing

Zhenghao Zhang, Ziying Zhang, Junchao Liao, Xiangyu Meng, Qiang Hu, Siyu Zhu +3

ICLR 2026poster

Recent multimodal models for instruction-based face editing enable semantic manipulation but still struggle with precise attribute control and identity preservation. Structural facial representations such as landmarks are effective for intermediate supervision, yet most existing methods treat them a…

Cited by 0 Source ↗code ↗Scholar ↗

2023

DR2: Diffusion-Based Robust Degradation Remover for Blind Face Restoration

Zhixin Wang, Ziying Zhang, Xiaoyun Zhang, Huangjie Zheng, Mingyuan Zhou, Ya Zhang +1

CVPR 2023poster

Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the restoration performance where artifacts are often observed in…

Cited by 96 Source ↗PDF ↗code ↗Scholar ↗