Burst Denoising with Kernel Prediction Networks

Authors:
  • BMBen Mildenhall
    Ben Mildenhall
  • JBJonathan T. Barron
    Jonathan T. Barron
  • JCJiawen Chen
    Jiawen Chen
  • DSDillon Sharlet
    Dillon Sharlet
  • RNRen Ng
    Ren Ng
  • RCRobert Carroll
    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.

This publication has 18 references indexed in Scilit: