SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.03472 · CVPR · 2023

Structured Kernel Estimation for Photon-Limited Deconvolution

Stanley Chan, Zhiyuan Mao, Yash Sanghvi

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Images taken in a low light condition with the presence of camera shake suffer from motion blur and photon shot noise. While state-of-the-art image restoration networks show promising results, they are largely limited to well-illuminated scenes and their performance drops significantly when photon shot noise is strong. In this paper, we propose a new blur estimation technique customized for photon-limited conditions. The proposed method employs a gradient-based backpropagation method to estimate the blur kernel. 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. When plugged into an iterative framework, our novel low-dimensional representation provides improved kernel estimates and hence significantly better deconvolution performance when compared to end-to-end trained neural networks. The source code and pretrained mdoels are available at https://github. com / sanghviyashiitb / structured -kernel -cvpr23 Vectorize

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.03472")
get_code_for_paper("2303.03472")
have("2303.03472")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.03472.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.03472.svg)](https://syntology.ai/paper/2303.03472)

Connect an agent — have() is free.