Burst Denoising with Kernel Prediction Networks
2017
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:
- Correction
- Cite
- Save
- Machine Reading By IdeaReader
23
References
6
Citations
NaN
KQI