# Burst Denoising with Kernel Prediction Networks

arXiv: https://arxiv.org/abs/1712.02327 · HTML: https://mlsanity.com/paper/1712.02327/

## Key facts

- Cited by 157 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2017.

## Built on by (most cited first, 30 of 157)

- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond](https://mlsanity.com/paper/2105.10422/) (2021)
- [Iterative Filter Adaptive Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2108.13610/) (2021)
- [Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --](https://mlsanity.com/paper/2301.03362/) (2023)
- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [Physics-based Noise Modeling for Extreme Low-light Photography](https://mlsanity.com/paper/2108.02158/) (2021)
- [Burst Image Restoration and Enhancement](https://mlsanity.com/paper/2110.03680/) (2021)
- [Mobile Computational Photography: A Tour](https://mlsanity.com/paper/2102.09000/) (2021)
- [Rethinking Noise Synthesis and Modeling in Raw Denoising](https://mlsanity.com/paper/2110.04756/) (2021)
- [Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging](https://mlsanity.com/paper/2103.07152/) (2021)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [Omni-Dimensional Dynamic Convolution](https://mlsanity.com/paper/2209.07947/) (2022)
- [NAN: Noise-Aware NeRFs for Burst-Denoising](https://mlsanity.com/paper/2204.04668/) (2022)
- [Dancing under the stars: video denoising in starlight](https://mlsanity.com/paper/2204.04210/) (2022)
- [Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communication](https://mlsanity.com/paper/2212.08273/) (2022)
- [Learning to Deblur using Light Field Generated and Real Defocus Images](https://mlsanity.com/paper/2204.00367/) (2022)
- [Deep Reparametrization of Multi-Frame Super-Resolution and Denoising](https://mlsanity.com/paper/2108.08286/) (2021)
- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [IDR: Self-Supervised Image Denoising via Iterative Data Refinement](https://mlsanity.com/paper/2111.14358/) (2021)
- [RobustSAM: Segment Anything Robustly on Degraded Images](https://mlsanity.com/paper/2406.09627/) (2024)
- [Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV](https://mlsanity.com/paper/2407.11087/) (2024)
- [MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting](https://mlsanity.com/paper/2203.06304/) (2022)
- [Learning Degradation Representations for Image Deblurring](https://mlsanity.com/paper/2208.05244/) (2022)
- [Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption](https://mlsanity.com/paper/2312.09093/) (2023)
- [KBNet: Kernel Basis Network for Image Restoration](https://mlsanity.com/paper/2303.02881/) (2023)
- [Burstormer: Burst Image Restoration and Enhancement Transformer](https://mlsanity.com/paper/2304.01194/) (2023)
- [Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network](https://mlsanity.com/paper/2104.09556/) (2021)
- [MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network](https://mlsanity.com/paper/2304.01598/) (2023)

## Abstract (arXiv)

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.