Xuanmeng Zhang

Xuanmeng Zhang 张轩梦

I am a final-year Ph.D. student at University of Technology Sydney. Prior to this, I graduated from Chu Kochen Honors College at Zhejiang University. I also spent wonderful time at Baidu, Alibaba, ByteDance, and National University Singapore.

Email / CV / Scholar / Linkedin / Github

Contact: zhangxuanmeng.zxm@gmail.com

I am currently seeking job opportunities. If there are suitable positions available, please feel free to reach out. Thank you!

Research

I'm interested in computer vision, generative models, and 3D vision.

	AvatarStudio: High-Fidelity and Animatable 3D Avatar Creation from Text Xuanmeng Zhang, Jianfeng Zhang, Chenxu Zhang, Jun Hao Liew, Huichao Zhang, Yi Yang, Jiashi Feng IJCV, 2025 project page / paper / bibtex AvatarStudio can create high-quality avatars from text that are ready for animation.
	Self-ensembling Depth Completion via Density-aware Consistency Xuanmeng Zhang, Zhedong Zheng, Minyue Jiang, Xiaoqing Ye PR, 2025 paper / bibtex We propose SEED, a SElf-Ensembling Depth completion framework to enhance the generalization of the model on unlabeled data.
	Multi-view Consistent Generative Adversarial Networks for Compositional 3d-aware Image Synthesis Xuanmeng Zhang, Zhedong Zheng, Daiheng Gao, Bang Zhang, Yi Yang, Tat-Seng Chua IJCV, 2023 paper / bibtex We study compositional 3D-aware image synthesis for both single-object and multi-object scenes.
	Getavatar: Generative Textured Meshes for Animatable Human Avatars Xuanmeng Zhang, Jianfeng Zhang, Rohan Chacko, Hongyi Xu, Guoxian Song, Yi Yang, Jiashi Feng ICCV, 2023 project page / paper / code / bibtex We introduce GETAvatar, a Generative model that directly generates Explicit Textured 3D meshes for animatable human Avatar, with photo-realistic appearance and fine geometric details.
	Multi-view Consistent Generative Adversarial Networks for 3d-aware Image Synthesis Xuanmeng Zhang, Zhedong Zheng, Daiheng Gao, Bang Zhang, Pan Pan, Yi Yang CVPR, 2022 paper / code / bibtex We propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints.
	Robust Vehicle Re-identification via Rigid Structure Prior Minyue Jiang, Xuanmeng Zhang*, Yue Yu, Zechen Bai, Zhedong Zheng, Zhigang Wang, Jian Wang, Xiao Tan, Hao Sun, Errui Ding, Yi Yang CVPR Workshops*, 2021 paper / code / bibtex The runner-up solution of AICITY Challenge Track2 (Vehicle Re-Identification) at CVPR 2021.

Template from Jon Barron.