Burst Denoising with Kernel Prediction Networks
This addresses image quality issues for photographers and mobile users, but it is incremental as it builds on existing burst denoising methods.
The paper tackled the problem of denoising bursts of images from handheld cameras by proposing a convolutional neural network that predicts spatially varying kernels for alignment and denoising, achieving state-of-the-art performance across various noise levels on real and synthetic data.
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.