Burst Denoising With Kernel Prediction Networks

Ben Mildenhall; Jonathan T. Barron; Jiawen Chen; Dillon Sharlet; Ren Ng; Robert Carroll

CVPR 2018poster467 citations

Burst Denoising With Kernel Prediction Networks

Ben Mildenhall, Jonathan T. Barron, Jiawen Chen, Dillon Sharlet, Ren Ng, Robert Carroll

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.

BibTeX

@inproceedings{cvpr2018_burstdenoisingwi,
  title = {Burst Denoising With Kernel Prediction Networks},
  author = {Ben Mildenhall and Jonathan T. Barron and Jiawen Chen and Dillon Sharlet and Ren Ng and Robert Carroll},
  booktitle = {CVPR 2018},
  year = {2018}
}