Burst Denoising with Kernel Prediction Networks

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...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2502 - 2510
Main Authors Mildenhall, Ben, Barron, Jonathan T., Chen, Jiawen, Sharlet, Dillon, Ng, Ren, Carroll, Robert
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Cameras
Computer architecture
Kernel
Noise measurement
Noise reduction
Task analysis
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00265