Search Results for author: Zhiyuan Mao

Found 9 papers, 4 papers with code

Structured Kernel Estimation for Photon-Limited Deconvolution

1 code implementation6 Mar 2023 Yash Sanghvi, Zhiyuan Mao, Stanley H. Chan

By modeling the blur kernel using a low-dimensional representation with the key points on the motion trajectory, we significantly reduce the search space and improve the regularity of the kernel estimation problem.

Image Restoration

Real-Time Dense Field Phase-to-Space Simulation of Imaging through Atmospheric Turbulence

no code implementations13 Oct 2022 Nicholas Chimitt, Xingguang Zhang, Zhiyuan Mao, Stanley H. Chan

We show that the cross-correlation of the Zernike modes has an insignificant contribution to the statistics of the random samples.

Photon-Limited Blind Deconvolution using Unsupervised Iterative Kernel Estimation

1 code implementation31 Jul 2022 Yash Sanghvi, Abhiram Gnanasambandam, Zhiyuan Mao, Stanley H. Chan

When the noise is strong, these networks fail to simultaneously deblur and denoise; (3) While iterative schemes are known to be robust in the classical frameworks, they are seldom considered in deep neural networks because it requires a differentiable non-blind solver.

Image Restoration

Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model

1 code implementation20 Jul 2022 Zhiyuan Mao, Ajay Jaiswal, Zhangyang Wang, Stanley H. Chan

Image restoration algorithms for atmospheric turbulence are known to be much more challenging to design than traditional ones such as blur or noise because the distortion caused by the turbulence is an entanglement of spatially varying blur, geometric distortion, and sensor noise.

Image Restoration SSIM

Imaging through the Atmosphere using Turbulence Mitigation Transformer

no code implementations13 Jul 2022 Xingguang Zhang, Zhiyuan Mao, Nicholas Chimitt, Stanley H. Chan

The new data synthesis process enables the generation of large-scale multi-level turbulence and ground truth pairs for training.

Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform

1 code implementation ICCV 2021 Zhiyuan Mao, Nicholas Chimitt, Stanley H. Chan

Fast and accurate simulation of imaging through atmospheric turbulence is essential for developing turbulence mitigation algorithms.

Student-Teacher Learning from Clean Inputs to Noisy Inputs

no code implementations CVPR 2021 Guanzhe Hong, Zhiyuan Mao, Xiaojun Lin, Stanley H. Chan

Feature-based student-teacher learning, a training method that encourages the student's hidden features to mimic those of the teacher network, is empirically successful in transferring the knowledge from a pre-trained teacher network to the student network.

Image Reconstruction of Static and Dynamic Scenes through Anisoplanatic Turbulence

no code implementations31 Aug 2020 Zhiyuan Mao, Nicholas Chimitt, Stanley Chan

Ground based long-range passive imaging systems often suffer from degraded image quality due to a turbulent atmosphere.

Image Reconstruction

Rethinking Atmospheric Turbulence Mitigation

no code implementations17 May 2019 Nicholas Chimitt, Zhiyuan Mao, Guanzhe Hong, Stanley H. Chan

We demonstrate how a simple prior can outperform state-of-the-art blind deconvolution methods.

Image Restoration Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.