English

Burst Denoising with Kernel Prediction Networks

Computer Vision and Pattern Recognition 2018-03-30 v2

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.

Keywords

Cite

@article{arxiv.1712.02327,
  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},
  journal= {arXiv preprint arXiv:1712.02327},
  year   = {2018}
}

Comments

To appear in CVPR 2018 (spotlight). Project page: http://people.eecs.berkeley.edu/~bmild/kpn/

R2 v1 2026-06-22T23:10:11.547Z