# Multi-Kernel Prediction Networks for Denoising of Burst Images

## TL;DR

This paper introduces Multi-Kernel Prediction Networks (MKPN), a deep learning approach for burst image denoising that predicts and fuses kernels of various sizes to improve noise reduction and image clarity in low-light conditions.

## Contribution

The paper presents a novel neural network architecture that predicts multiple kernel sizes and fuses them for enhanced burst image denoising, outperforming existing methods.

## Key findings

- MKPN achieves superior denoising performance on synthetic datasets.
- Using multiple kernel sizes improves feature extraction and image reconstruction.
- Kernel fusion maintains efficiency while enhancing denoising quality.

## Abstract

In low light or short-exposure photography the image is often corrupted by noise. While longer exposure helps reduce the noise, it can produce blurry results due to the object and camera motion. The reconstruction of a noise-less image is an ill posed problem. Recent approaches for image denoising aim to predict kernels which are convolved with a set of successively taken images (burst) to obtain a clear image. We propose a deep neural network based approach called Multi-Kernel Prediction Networks (MKPN) for burst image denoising. MKPN predicts kernels of not just one size but of varying sizes and performs fusion of these different kernels resulting in one kernel per pixel. The advantages of our method are two fold: (a) the different sized kernels help in extracting different information from the image which results in better reconstruction and (b) kernel fusion assures retaining of the extracted information while maintaining computational efficiency. Experimental results reveal that MKPN outperforms state-of-the-art on our synthetic datasets with different noise levels.