Vision Laboratory at Yale University

Research

Our lab tackles a variety of problems, including fusing multi-modal data for inferring properties of the 3-dimensional (3D) scene, unsupervised and weakly supervised learning in application towards 3D reconstruction and semantics, robust perception under adverse conditions, as well as medical image analysis. Check out some of our publications below!

Publications

2025

ETA: Energy-based Test-time Adaptation for Depth Completion
ETA: Energy-based Test-time Adaptation for Depth Completion
Younjoon Chung, Hyoungseob Park, Patrick Rim, Xiaoran Zhang, Jihe He, Ziyao Zeng, Safa Cicek, Byung-Woo Hong, James S. Duncan, Alex Wong
2025 IEEE/CVF International Conference on Computer Vision (ICCV)   ·   19 Oct 2025   ·   2508.05989 To appear in proceedings
Source
Paper
Progressive Test Time Energy Adaptation for Medical Image Segmentation
Progressive Test Time Energy Adaptation for Medical Image Segmentation
Xiaoran Zhang, Byung-Woo Hong, Hyoungseob Park, Daniel H. Pak, Anne-Marie Rickmann, Lawrence H. Staib, James S. Duncan, Alex Wong
2025 IEEE/CVF International Conference on Computer Vision (ICCV)   ·   19 Oct 2025   ·   2503.16616 To appear in proceedings
Source
Paper
Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens
Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens
Suchisrit Gangopadhyay, Jung-Hee Kim, Xien Chen, Patrick Rim, Hyoungseob Park, Alex Wong
2025 IEEE/CVF International Conference on Computer Vision (ICCV)   ·   19 Oct 2025   ·   2508.04928 To appear in proceedings
Source
Paper
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
Patrick Rim, Hyoungseob Park, S. Gangopadhyay, Ziyao Zeng, Younjoon Chung, Alex Wong
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   11 Jun 2025   ·   doi:10.1109/cvpr52734.2025.00591
Source
Paper
Forces for free: Vision-based contact force estimation with a compliant hand
Forces for free: Vision-based contact force estimation with a compliant hand
Yifan Zhu, Mei Hao, Xupeng Zhu, Quentin Bateux, Alex Wong, Aaron M. Dollar
Science Robotics   ·   08 Jun 2025   ·   doi:10.1126/scirobotics.adq5046
Source
Paper

2024

RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
Ziyao Zeng, Yangchao Wu, Hyoungseob Park, Daniel Wang, Fengyu Yang, Stefano Soatto, Dong Lao, Byung-Woo Hong, Alex Wong
Advances in Neural Information Processing Systems 37 (NeurIPS 2024)   ·   10 Dec 2024   ·   doi:10.5555/3737916.3741496
Source
Paper
All-day Depth Completion
All-day Depth Completion
Vadim Ezhov, Hyoungseob Park, Zhaoyang Zhang, Rishi Upadhyay, Howard Zhang, Chetan Chinder Chandrappa, Achuta Kadambi, Yunhao Ba, Julie Dorsey, Alex Wong
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)   ·   14 Oct 2024   ·   doi:10.1109/iros58592.2024.10802376
Source
Paper
Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration
Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration
Xiaoran Zhang, Daniel H. Pak, Shawn S. Ahn, Xiaoxiao Li, Chenyu You, Lawrence H. Staib, Albert J. Sinusas, Alex Wong, James S. Duncan
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2024   ·   04 Oct 2024   ·   doi:10.1007/978-3-031-72069-7_61
Source
Paper
On the Viability of Monocular Depth Pre-training for Semantic Segmentation
On the Viability of Monocular Depth Pre-training for Semantic Segmentation
Dong Lao, Fengyu Yang, Daniel Wang, Hyoungseob Park, Samuel Lu, Alex Wong, Stefano Soatto
2024 European Conference on Computer Vision (ECCV)   ·   08 Sep 2024   ·   doi:10.1007/978-3-031-72913-3_19
Source
Paper
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
Yangchao Wu, Tian Yu Liu, Hyoungseob Park, Stefano Soatto, Dong Lao, Alex Wong
2024 European Conference on Computer Vision (ECCV)   ·   08 Sep 2024   ·   doi:10.1007/978-3-031-73039-9_16
Source
Paper
Adaptive Correspondence Scoring for Unsupervised Medical Image Registration
Adaptive Correspondence Scoring for Unsupervised Medical Image Registration
Xiaoran Zhang, John C. Stendahl, Lawrence Staib, Albert J. Sinusas, Alex Wong, James S. Duncan
2024 European Conference on Computer Vision (ECCV)   ·   08 Sep 2024   ·   doi:10.1007/978-3-031-72920-1_5
Source
Paper
Sub-token ViT Embedding via Stochastic Resonance Transformers
Sub-token ViT Embedding via Stochastic Resonance Transformers
Dong Lao, Yangchao Wu, Tian Yu Liu, Alex Wong, Stefano Soatto
International Conference on Machine Learning (ICML) 2024   ·   21 Jul 2024   ·   2310.03967 - To appear in proceedings
Source
Paper
WorDepth: Variational Language Prior for Monocular Depth Estimation
WorDepth: Variational Language Prior for Monocular Depth Estimation
Ziyao Zeng, Hyoungseob Park, Fengyu Yang, Daniel Wang, Stefano Soatto, Dong Lao, Alex Wong
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   17 Jun 2024   ·   doi:10.1109/cvpr52733.2024.00927
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
Dong Lao, Congli Wang, Alex Wong, Stefano Soatto
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   17 Jun 2024   ·   doi:10.1109/cvpr52733.2024.02372
Binding touch to everything: Learning unified multimodal tactile representations
Binding touch to everything: Learning unified multimodal tactile representations
Fengyu Yang, Chao Feng, Ziyang Chen, Hyoungseob Park, Daniel Wang, ..., Ziyao Zeng, Xien Chen, Rit Gangopadhyay, Andrew Owens, Alex Wong
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   17 Jun 2024   ·   doi:10.1109/cvpr52733.2024.02488
Source
Paper
Test-Time Adaptation for Depth Completion
Test-Time Adaptation for Depth Completion
Hyoungseob Park, Anjali Gupta, Alex Wong
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   17 Jun 2024   ·   doi:10.1109/cvpr52733.2024.01939
Source
Paper

2023

Enhancing Diffusion Models with 3D Perspective Geometry Constraints
Enhancing Diffusion Models with 3D Perspective Geometry Constraints
Rishi Upadhyay, Howard Zhang, Yunhao Ba, Ethan Yang, Blake Gella, Sicheng Jiang, Alex Wong, Achuta Kadambi
AMC SIGGRAPH Asia 2023   ·   05 Dec 2023   ·   doi:10.1145/3618389
Source
Paper
Depth Estimation from Camera Image and mmWave Radar Point Cloud
Depth Estimation from Camera Image and mmWave Radar Point Cloud
Akash Deep Singh, Yunhao Ba, Ankur Sarker, Howard Zhang, Achuta Kadambi, Stefano Soatto, Mani Srivastava, Alex Wong
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   01 Jun 2023   ·   doi:10.1109/cvpr52729.2023.00895
Source
Paper
WeatherStream: Light Transport Automation of Single Image Deweathering
WeatherStream: Light Transport Automation of Single Image Deweathering
Howard Zhang, Yunhao Ba, Ethan Yang, Varan Mehra, Blake Gella, Akira Suzuki, Arnold Pfahnl, Chethan Chinder Chandrappa, Alex Wong, Achuta Kadambi
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   01 Jun 2023   ·   doi:10.1109/cvpr52729.2023.01297
Source
Paper
Spatial Mapping of Mitochondrial Networks and Bioenergetics in Lung Cancer
Spatial Mapping of Mitochondrial Networks and Bioenergetics in Lung Cancer
Mingqi Han, Eric A. Bushong, Mayuko Segawa, Alexandre Tiard, Alex Wong, ..., Aaron Lisberg, Stefano Soatto, Saman Sadeghi, Mark H. Ellisman, David B. Shackelford
Nature   ·   15 Mar 2023   ·   doi:10.1038/s41586-023-05793-3
Source

2022

Stereoscopic Universal Perturbations across Different Architectures and Datasets
Stereoscopic Universal Perturbations across Different Architectures and Datasets
Zachary Berger, Parth Agrawal, Tian Yu Liu, Stefano Soatto, Alex Wong
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   01 Jun 2022   ·   doi:10.1109/cvpr52688.2022.01475
Source
Paper
Small Lesion Segmentation in Brain MRIs with Subpixel Embedding (Oral)
Small Lesion Segmentation in Brain MRIs with Subpixel Embedding (Oral)
Alex Wong, Allison Chen, Yangchao Wu, Safa Cicek, Alexandre Tiard, Byung-Woo Hong, Stefano Soatto
Lecture Notes in Computer Science   ·   01 Jan 2022   ·   doi:10.1007/978-3-031-08999-2_6
Source
Paper
Not Just Streaks: Towards Ground Truth for Single Image Deraining
Not Just Streaks: Towards Ground Truth for Single Image Deraining
Yunhao Ba, Howard Zhang, Ethan Yang, Akira Suzuki, Arnold Pfahnl, ..., Celso M. de Melo, Suya You, Stefano Soatto, Alex Wong, Achuta Kadambi
Lecture Notes in Computer Science   ·   01 Jan 2022   ·   doi:10.1007/978-3-031-20071-7_42
Source
Paper
Monitored Distillation for Positive Congruent Depth Completion
Monitored Distillation for Positive Congruent Depth Completion
Tian Yu Liu, Parth Agrawal, Allison Chen, Byung-Woo Hong, Alex Wong
Lecture Notes in Computer Science   ·   01 Jan 2022   ·   doi:10.1007/978-3-031-20086-1_3
Source
Paper

2021

Unsupervised Depth Completion with Calibrated Backprojection Layers (Oral)
Unsupervised Depth Completion with Calibrated Backprojection Layers (Oral)
Alex Wong, Stefano Soatto
2021 IEEE/CVF International Conference on Computer Vision (ICCV)   ·   01 Oct 2021   ·   doi:10.1109/iccv48922.2021.01251
Source
Paper
Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations
Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations
Alex Wong, Mukund Mundhra, Stefano Soatto
Proceedings of the AAAI Conference on Artificial Intelligence   ·   18 May 2021   ·   doi:10.1609/aaai.v35i4.16394
Source
Paper
An Adaptive Framework for Learning Unsupervised Depth Completion
An Adaptive Framework for Learning Unsupervised Depth Completion
Alex Wong, Xiaohan Fei, Byung-Woo Hong, Stefano Soatto
IEEE Robotics and Automation Letters   ·   01 Apr 2021   ·   doi:10.1109/LRA.2021.3062602
Source
Paper
Learning Topology From Synthetic Data for Unsupervised Depth Completion
Learning Topology From Synthetic Data for Unsupervised Depth Completion
Alex Wong, Safa Cicek, Stefano Soatto
IEEE Robotics and Automation Letters   ·   01 Apr 2021   ·   doi:10.1109/LRA.2021.3058072
Source
Paper

2020

Targeted Adversarial Perturbations for Monocular Depth Prediction
Targeted Adversarial Perturbations for Monocular Depth Prediction
Alex Wong, Safa Cicek, Stefano Soatto
Advances in Neural Information Processing Systems   ·   20 Dec 2020   ·   https://dl.acm.org/doi/10.5555/3495724.3496435
Source
Paper
Unsupervised Depth Completion From Visual Inertial Odometry
Unsupervised Depth Completion From Visual Inertial Odometry
Alex Wong, Xiaohan Fei, Stephanie Tsuei, Stefano Soatto
IEEE Robotics and Automation Letters   ·   01 Apr 2020   ·   doi:10.1109/lra.2020.2969938
Source
Paper

2019

Dense Depth Posterior (DDP) From Single Image and Sparse Range
Dense Depth Posterior (DDP) From Single Image and Sparse Range
Yanchao Yang, Alex Wong, Stefano Soatto
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   01 Jun 2019   ·   doi:10.1109/cvpr.2019.00347
Paper
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction
Alex Wong, Stefano Soatto
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)   ·   01 Jun 2019   ·   doi:10.1109/cvpr.2019.00579
Source
Paper
Geo-Supervised Visual Depth Prediction (Best Paper Award in Robot Vision)
Geo-Supervised Visual Depth Prediction (Best Paper Award in Robot Vision)
Xiaohan Fei, Alex Wong, Stefano Soatto
IEEE Robotics and Automation Letters   ·   01 Apr 2019   ·   doi:10.1109/lra.2019.2896963
Source
Paper

2017

Exploiting Protrusion Cues for Fast and Effective Shape Modeling via Ellipses
Exploiting Protrusion Cues for Fast and Effective Shape Modeling via Ellipses
Alex Wong, Alan Yuille, Brian Taylor
Procedings of the British Machine Vision Conference 2017   ·   01 Jan 2017   ·   doi:10.5244/c.31.174

2015

One Shot Learning via Compositions of Meaningful Patches
One Shot Learning via Compositions of Meaningful Patches
Alex Wong, Alan Yuille
2015 IEEE International Conference on Computer Vision (ICCV)   ·   01 Dec 2015   ·   doi:10.1109/iccv.2015.142

2011

Fast and Accurate k-means for Large Datasets (Outstanding Student Paper Award)
Fast and Accurate k-means for Large Datasets (Outstanding Student Paper Award)
Michael Shindler, Alex Wong, Adam Meyerson
Advances in Neural Information Processing Systems   ·   12 Dec 2011   ·   https://dl.acm.org/doi/10.5555/2986459.2986724
Paper