# Robust estimation of exposure ratios in multi-exposure image stacks

arXiv: https://arxiv.org/abs/2308.02968 · HTML: https://mlsanity.com/paper/2308.02968/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 50 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 13 of 13)

- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results](https://mlsanity.com/paper/2106.01439/) (2021)
- [Learning Camera-Aware Noise Models](https://mlsanity.com/paper/2008.09370/) (2020)
- [Image Correction via Deep Reciprocating HDR Transformation](https://mlsanity.com/paper/1804.04371/) (2018)
- [High-level numerical simulations of noise in CCD and CMOS photosensors: review and tutorial](https://mlsanity.com/paper/1412.4031/) (2014)
- [Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration](https://mlsanity.com/paper/2107.06211/) (2021)
- [BBAND Index: A No-Reference Banding Artifact Predictor](https://mlsanity.com/paper/2002.11891/) (2020)
- [Progressive and Selective Fusion Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2108.08585/) (2021)
- [Noise-Aware Merging of High Dynamic Range Image Stacks without Camera Calibration](https://mlsanity.com/paper/2009.07975/) (2020)
- [Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting](https://mlsanity.com/paper/2112.13050/) (2021)

## Built on by (most cited first, 3 of 3)

- [X2HDR: HDR Image Generation in a Perceptually Uniform Space](https://mlsanity.com/paper/2602.04814/) (2026)
- [Multi-exposure HDR Imaging: A Review of Pixel-level and Feature-level Reconstruction Methods](https://mlsanity.com/paper/2608.28674/) (2026)
- [Single-Shot HDR Recovery via a Video Diffusion Prior](https://mlsanity.com/paper/2605.11628/) (2026)

## Abstract (arXiv)

Merging multi-exposure image stacks into a high dynamic range (HDR) image requires knowledge of accurate exposure times. When exposure times are inaccurate, for example, when they are extracted from a camera's EXIF metadata, the reconstructed HDR images reveal banding artifacts at smooth gradients. To remedy this, we propose to estimate exposure ratios directly from the input images. We derive the exposure time estimation as an optimization problem, in which pixels are selected from pairs of exposures to minimize estimation error caused by camera noise. When pixel values are represented in the logarithmic domain, the problem can be solved efficiently using a linear solver. We demonstrate that the estimation can be easily made robust to pixel misalignment caused by camera or object motion by collecting pixels from multiple spatial tiles. The proposed automatic exposure estimation and alignment eliminates banding artifacts in popular datasets and is essential for applications that require physically accurate reconstructions, such as measuring the modulation transfer function of a display. The code for the method is available.