⬆️ Try to drag around!! ⬆️

Figure 1. Zhaoning Wang when he finally realize why there are only straight faces in NeRF datasets.

About me

I am Zhaoning Wang, currently an incoming PhD student at University of Michigan, advised by Prof. Jun Gao.

I am interested in using state-of-the-art deep learning and computer vision to improve machine perceptions and let them aware of their surroundings.

I am particularly interested in 3D Neural Representations, 3D reconstructions, Generative Networks and Foundation Models. I am also keen on data-driven computer vision or synthetic data. I believe these will fundamentally help to bridge the gap between the virtual and physical world, i.e. Computers and Reality, and enabling the next generation of embodied AI systems.

I’m always open to research collaborations in this area. Feel free to drop me an email at :

zhaoning [dot] eric [dot] wang [at] gmail [dot] com.

Publications

MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Minghua Liu*, Chong Zeng*, Xinyue Wei, Ruoxi Shi, Linghao Chen, Chao Xu, Mengqi Zhang, Zhaoning Wang, Xiaoshuai Zhang, Isabella Liu, Hongzhi Wu, Hao Su.
Conference on Neural Information Processing Systems (NeurIPS) [Oral], 2024

LucidDreaming: Controllable Object-Centric 3D Generation
European Conference on Computer Vision (ECCV) Workshop, 2024

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.
Ming Li, Taojiannan Yang, Huafeng Kuang, Jie Wu, Zhaoning Wang, Xuefeng Xiao, Chen Chen.
European Conference on Computer Vision (ECCV), 2024

VOS: Learning What You Don’t Know by Virtual Outliers Synthesis.
International Conference on Learning Representations (ICLR), 2022

ZOOM: Zero-shot Model Diagnosis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023