Peng Zheng

I'm a PhD student in the MHUG group at the University of Trento, advised by Prof. Nicu Sebe, working on Image Segmentation, Object Retrieval, and AI for Biology. Before that, I spent years sequentially at IIAI, MBZUAI, Alibaba, Shanghai AI Lab as research assistant or research intern. I obtained my MSc at the University of Trento and Aalto University through the EIT Digital programme, and my BEng at Hebei Normal University. I'm the inventor and maintainer of the BiRefNet.

Peng Zheng

News

Selected Publications

Visit my google scholar for a full list.

Bilateral Reference for High-Resolution Dichotomous Image Segmentation
Peng Zheng, Dehong Gao, Deng-Ping Fan*, Li Liu, Jorma Laaksonen, Wanli Ouyang, Nicu Sebe
CAAI Artificial Intelligence Research (CAAI AIR), 2024
code / HF model (20M+ downloads) / HF demo

BiRefNet, a bilateral reference network for high-resolution dichotomous image segmentation. So far (by 2026), the best open-souce model for automatic background removal and subject extraction.

GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
Peng Zheng+, Huazhu Fu+, Deng-Ping Fan*, Qi Fan, Jie Qin, Yu-Wing Tai, Chi-Keung Tang, Luc Van Gool
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
code / demo

A stronger group collaborative network for co-salient object detection.

MovieNet-PS: A Large-Scale Person Search Dataset in the Wild
Jie Qin, Peng Zheng, Yichao Yan*, Quan Rong*, Xiaogang Cheng, Bingbing Ni
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
code / dataset

A large-scale person search dataset and benchmark in unconstrained settings.