Kevin W. Zhang
I'm currently a research scientist at Waabi, working on 4D foundation models for autonomous vehicle sensor simulation.I did a CS PhD at the University of Maryland, College Park, working with Christopher Metzler and Jia-Bin Huang on computer vision and computational imaging. Previously, I interned at Adobe Research in SF, where I worked with Aaron Hertzmann, and completed a BA in Computer Science and Pure Mathematics at UC Berkeley, advised by Laura Waller and Michael Lustig.
Updates
2026-07
Moved to SF and joined Waabi as a research scientist.
2026-04
Defended my PhD at UMD CP. Thanks to my advisors Chris and Jiabin and many other people for the support throughout the years!
2025-06
Acoustic Neural 3D Reconstruction Under Pose Drift accepted at IROS 2025. Congratulations to Tianxiang and Mohamad!
2025-06
Presented MaDCoW at CVPR 2025.
2025-05
Started a research internship on Marc Levoy's computational imaging team at Adobe.
Publications (* indicates equal contribution)
Select Publications
MaDCoW: Marginal Distortion Correction for Wide-Angle Photography with Arbitrary Objects
Kevin Zhang, Jia-Bin Huang, Jose Echevarria, Stephen DiVerdi, Aaron Hertzmann
CVPR 2025
[Paper]
Kevin Zhang, Jia-Bin Huang, Jose Echevarria, Stephen DiVerdi, Aaron Hertzmann
CVPR 2025
[Paper]
AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusion
Kevin Zhang*, Mohamad Qadri*, Akshay Hinduja, Michael Kaess, Adithya Pediredla, Christopher Metzler
SIGGRAPH 2024 (conference track full paper)
[Paper] [Website]
Kevin Zhang*, Mohamad Qadri*, Akshay Hinduja, Michael Kaess, Adithya Pediredla, Christopher Metzler
SIGGRAPH 2024 (conference track full paper)
[Paper] [Website]
Seeing the World through Your Eyes
Kevin Zhang*, Hadi AlZayer*, Brandon Feng, Christopher Metzler, Jia-bin Huang
CVPR 2024 (Oral, top 0.78% of submitted papers)
[Paper] [Website] [Press] [Twitter]
Kevin Zhang*, Hadi AlZayer*, Brandon Feng, Christopher Metzler, Jia-bin Huang
CVPR 2024 (Oral, top 0.78% of submitted papers)
[Paper] [Website] [Press] [Twitter]
Acoustic Neural 3D Reconstruction Under Pose Drift
Tianxiang Lin*, Mohamad Qadri*, Kevin Zhang, Adithya Pediredla, Christopher Metzler, Michael Kaess
IROS 2025
[Paper]
Tianxiang Lin*, Mohamad Qadri*, Kevin Zhang, Adithya Pediredla, Christopher Metzler, Michael Kaess
IROS 2025
[Paper]
A Scalable Training Strategy for Blind Multi-Distribution Noise Removal
Kevin Zhang, Sakshum Kulshrestha, Christopher Metzler
IEEE TIP 2024
[Paper]
Kevin Zhang, Sakshum Kulshrestha, Christopher Metzler
IEEE TIP 2024
[Paper]
Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion
Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri, Kevin Zhang, Michael Kaess, Christopher Metzler, Suren Jayasuriya, Adithya Pediredla
IEEE TPAMI 2024
[Paper]
Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri, Kevin Zhang, Michael Kaess, Christopher Metzler, Suren Jayasuriya, Adithya Pediredla
IEEE TPAMI 2024
[Paper]
Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations
Haoming Cai*, Jingxi Chen*, Brandon Y. Feng, Weiyun Jiang, Mingyang Xie, Kevin Zhang, Cornelia Fermuller, Yiannis Aloimonos, Ashok Veeraraghavan, Christopher Metzler
NeurIPS 2024
[Paper] [Website]
Haoming Cai*, Jingxi Chen*, Brandon Y. Feng, Weiyun Jiang, Mingyang Xie, Kevin Zhang, Cornelia Fermuller, Yiannis Aloimonos, Ashok Veeraraghavan, Christopher Metzler
NeurIPS 2024
[Paper] [Website]
PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters
Shuhong Chen, Kevin Zhang, Yichun Shi, Heng Wang, Yiheng Zhu, Guoxian Song, Sizhe An, Janus Þór Kristjánsson, Xiao Yang, Matthias Zwicker
CVPR 2023
[Paper] [Code]
Shuhong Chen, Kevin Zhang, Yichun Shi, Heng Wang, Yiheng Zhu, Guoxian Song, Sizhe An, Janus Þór Kristjánsson, Xiao Yang, Matthias Zwicker
CVPR 2023
[Paper] [Code]
MetaDIP: Accelerating Deep Image Prior with Meta Learning
Kevin Zhang, Mingyang Xie, Maharshi Gor, Yi-Ting Chen, Yvonne Zhou, Christopher Metzler
arXiv, 2022
[Paper]
Kevin Zhang, Mingyang Xie, Maharshi Gor, Yi-Ting Chen, Yvonne Zhou, Christopher Metzler
arXiv, 2022
[Paper]
Memory-efficient Learning for High-Dimensional MRI Reconstruction
Ke Wang, Christopher Sandino, Michael Kellman, Kevin Zhang, Shreyas Vasanawala, Jonathan I. Tamir, Stella Yu, Michael Lustig
MICCAI 2021
[Paper] [Code]
Ke Wang, Christopher Sandino, Michael Kellman, Kevin Zhang, Shreyas Vasanawala, Jonathan I. Tamir, Stella Yu, Michael Lustig
MICCAI 2021
[Paper] [Code]
Memory-efficient Learning for Large-scale Computational Imaging
Michael Kellman, Kevin Zhang, Eric Markley, Jonathan I. Tamir, Emrah Bostan, Michael Lustig, Laura Waller
IEEE TCI 2020
[Paper] [Code]
Michael Kellman, Kevin Zhang, Eric Markley, Jonathan I. Tamir, Emrah Bostan, Michael Lustig, Laura Waller
IEEE TCI 2020
[Paper] [Code]
Memory-Efficient Learning for Unrolled 3D MRI Reconstructions
Kevin Zhang*, Michael Kellman*, Jonathan I. Tamir, Michael Lustig, Laura Waller
ISMRM Workshop on Data Sampling and Reconstruction, 2020
[Paper] [Video]
Kevin Zhang*, Michael Kellman*, Jonathan I. Tamir, Michael Lustig, Laura Waller
ISMRM Workshop on Data Sampling and Reconstruction, 2020
[Paper] [Video]
3D fluorescence deconvolution with deep priors
Kevin Zhang, Michael Kellman, Emrah Bostan, Laura Waller
SPIE BiOS 2020
[Paper]
Kevin Zhang, Michael Kellman, Emrah Bostan, Laura Waller
SPIE BiOS 2020
[Paper]
Gratitude
I'm extremely grateful for the following friends - Daniel Xu, Rebecca Y. E. Lin, Zora Che, Brandon Y. Feng, Ani Nrusimha, Catherine Cang, and Anna Brewer.