Basis Prediction Networks for Effective Burst Denoising With Large Kernels

Zhihao Xia, Federico Perazzi, Michael Gharbi, Kalyan Sunkavalli, Ayan Chakrabarti; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 11844-11853

Abstract


Bursts of images exhibit significant self-similarity across both time and space. This motivates a representation of the kernels as linear combinations of a small set of basis elements. To this end, we introduce a novel basis prediction network that, given an input burst, predicts a set of global basis kernels --- shared within the image --- and the corresponding mixing coefficients --- which are specific to individual pixels. Compared to state-of-the-art techniques that output a large tensor of per-pixel spatiotemporal kernels, our formulation substantially reduces the dimensionality of the network output. This allows us to effectively exploit comparatively larger denoising kernels, achieving both significant quality improvements (over 1dB PSNR) and faster run-times over state-of-the-art methods.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2020_CVPR,
author = {Xia, Zhihao and Perazzi, Federico and Gharbi, Michael and Sunkavalli, Kalyan and Chakrabarti, Ayan},
title = {Basis Prediction Networks for Effective Burst Denoising With Large Kernels},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}