About
I am a PhD student in Computer Science at King Abdullah University of Science and Technology (KAUST) under Prof. Peter Wonka.
Prior to this, I obtained my M.S. degree in Electrical and Computer Engineering from KAUST, and my B.Eng. degree in Electronic Information Engineering from Harbin Institute of Technology (HIT), China.
My research interests include 3D Vision and Perception (Depth Estimation / Surface Normal Estimation).
Outside of research, I am an enthusiast of 🏀 basketball, 🏃 running, and 🥏 ultimate frisbee.
Selected Publications
View All →Any Resolution Any Geometry: From Multi-View To Multi-Patch
Wenqing Cui, Zhenyu Li†, Mykola Lavreniuk†, Jian Shi, Ramzi Idoughi, Xiangjun Tang, Peter Wonka
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
A multi-patch framework for high-resolution monocular depth and surface normal estimation at any resolution with sharp boundaries and globally consistent geometry.
PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation
Zhenyu Li, Wenqing Cui, Shariq Farooq Bhat, Peter Wonka
International Conference on Learning Representations (ICLR)
A fast and lightweight framework for high-resolution metric depth estimation that outperforms state-of-the-art methods in both accuracy and speed.
Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning
Jian Shi, Michael Birsak, Wenqing Cui, Zhenyu Li, Peter Wonka
arXiv preprint arXiv:2601.22231
A study revisiting positional embeddings in vision transformers from a geometric perspective, revealing their role as geometric priors for spatial reasoning.
StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart
Jian Shi, Qian Wang, Zhenyu Li, Ramzi Idoughi, Wenqing Cui, Peter Wonka
arXiv preprint arXiv:2411.14295
A zero-shot framework for stereo video generation using video diffusion priors with a noisy restart strategy, achieving state-of-the-art depth consistency.
News
Our paper Any Resolution Any Geometry has been accepted at CVPR 2026!
Our paper PatchRefiner V2 has been accepted at ICLR 2026!
Started PhD in Computer Science at KAUST.
Completed M.S. degree at KAUST.
Joined KAUST for M.S. in Electrical and Computer Engineering.
Graduated from Harbin Institute of Technology with B.Eng. degree.