P.hD, PI Shanghai AI Lab

Yiran Zhong is a principal investigator at Shanghai AI Laboratory. Prior to that, he received a Ph.D. degree in Engineering from The Australian National University, Canberra, Australia in 2021 and an M.Eng with the first class honor in information and electronics engineering from The Australian National University, Canberra, Australia, in 2014, and a B.E. degree from the University of Electronic Science and Technology of China in 2008. His research interests include self-supervised learning, visual geometry learning, multimodality learning, machine learning, and natural language processing. He won the ICIP Best Student Paper Award in 2014.


Doctor of Philosophy (2016 – 2020)
Supervisor: Prof. Hongdong Li, Prof. Yuchao Dai, Reader Henry Gardner, Prof. Nicholas Barnes, Prof. Richard Hartley @ ANU
Thesis: Self-supervised Visual Geometry Learning

Masters of Engineering (First Class Honor) (2012 – 2014)
Supervisor: Prof. Hongdong Li @ ANU
Thesis: Interactive 3D Reconstruction of Insects

Bachelor of Automation (2008 – 2012)
Thesis: Multi-media Sand Table System Design



Displacement-Invariant Cost Computation for Stereo Matching, IJCV, 2022

Implicit Motion Handling for Video Camouflaged Object Detection, CVPR, 2022

Deep Laparoscopic Stereo Matching with Transformers, MICCAI, 2022

Audio-Visual Segmentation, ECCV, 2022

cosFormer: Rethinking Softmax In Attention, ICLR, 2022

Transcribing Natural Languages for The Deaf via Neural Editing Programs, AAAI, 2022


Deep robust image deblurring via blur distilling and information comparison in latent space, Neurocomputing, 2021

Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding, TIP, 2021

RGB-D Saliency Detection via Cascaded Mutual Information Minimization, ICCV, 2021

Positive Sample Propagation along the Audio-Visual Event Line, CVPR, 2021

Deep Two-View Structure-from-Motion Revisited, CVPR, 2021

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring, CVPR, 2021


Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation, NeurIPS, 2020

Hierarchical Neural Architecture Search for Deep Stereo Matching, NeurIPS, 2020

Deblurring by realistic blurring, CVPR, 2020


Unsupervised deep epipolar flow for stationary or dynamic scenes, CVPR, 2019

Noise-aware unsupervised deep lidar-stereo fusion, CVPR, 2019


Adversarial spatio-temporal learning for video deblurring, TIP, 2018

3D geometry-aware semantic labeling of outdoor street scenes, ICPR, 2018

Open-world stereo video matching with deep rnn, ECCV, 2018

Stereo computation for a single mixture image, ECCV, 2018


Robust multi-body feature tracker: a segmentation-free approach, CVPR, 2016

Null space clustering with applications to motion segmentation and face clustering, ICIP, 2014