Burst Denoising With Kernel Prediction Networks

Ben Mildenhall, Jonathan T. Barron, Jiawen Chen, Dillon Sharlet, Ren Ng, Robert Carroll; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 2502-2510

Abstract

We present a technique for jointly denoising bursts of images taken from a handheld camera. In particular, we propose a convolutional neural network architecture for predicting spatially varying kernels that can both align and denoise frames, a synthetic data generation approach based on a realistic noise formation model, and an optimization guided by an annealed loss function to avoid undesirable local minima. Our model matches or outperforms the state-of-the-art across a wide range of noise levels on both real and synthetic data.

Related Material

[pdf] [supp] [arXiv] [video]
[bibtex]
@InProceedings{Mildenhall_2018_CVPR,
author = {Mildenhall, Ben and Barron, Jonathan T. and Chen, Jiawen and Sharlet, Dillon and Ng, Ren and Carroll, Robert},
title = {Burst Denoising With Kernel Prediction Networks},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}