mlsanityData to 7 Oct 2026

An Analysis and Implementation of the HDR+ Burst Denoising Method

arXiv 2110.09354 ↗First posted 18 Oct 2021eess.IV cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

HDR+ is an image processing pipeline presented by Google in 2016. At its core lies a denoising algorithm that uses a burst of raw images to produce a single higher quality image. Since it is designed as a versatile solution for smartphone cameras, it does not necessarily aim for the maximization of standard denoising metrics, but rather for the production of natural, visually pleasing images. In this article, we specifically discuss and analyze the HDR+ burst denoising algorithm architecture and the impact of its various parameters. With this publication, we provide an open source Python implementation of the algorithm, along with an interactive demo.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 5 of its 21 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

5 of 21 references.

References · 5

  1. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  2. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  3. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  4. 2019Handheld Mobile Photography in Very Low Lightcited by 56
  5. 2015Removing Camera Shake via Weighted Fourier Burst Accumulationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 5; 2026: 1.

8 papers.

  1. 2022High Dynamic Range and Super-Resolution from Raw Image Burstscited by 18
  2. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  3. 2023Joint Multi-Scale Tone Mapping and Denoising for HDR Image Enhancementcited by 7
  4. 2025Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Burstscited by 2
  5. 2025Deepfakes: we need to re-think the concept of "real" imagescited by 1
  6. 2025Self-Diffusion Driven Blind Imagingcited by 0
  7. 2025Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Taskscited by 0
  8. 2026Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detectioncited by 0