# AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes

arXiv: https://arxiv.org/abs/2508.13503 · HTML: https://mlsanity.com/paper/2508.13503/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [SalGAN: Visual Saliency Prediction with Generative Adversarial Networks](https://mlsanity.com/paper/1701.01081/) (2017)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring](https://mlsanity.com/paper/2101.07518/) (2021)
- [HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset](https://mlsanity.com/paper/2103.14943/) (2021)
- [TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learning](https://mlsanity.com/paper/2112.01030/) (2021)
- [HDRFlow: Real-Time HDR Video Reconstruction with Large Motions](https://mlsanity.com/paper/2403.03447/) (2024)
- [SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging](https://mlsanity.com/paper/2407.16308/) (2024)
- [Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network](https://mlsanity.com/paper/2405.00244/) (2024)
- [Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes](https://mlsanity.com/paper/2310.01840/) (2023)
- [Learning a Reinforced Agent for Flexible Exposure Bracketing Selection](https://mlsanity.com/paper/2005.12536/) (2020)
- [Improved Image Selection for Stack-Based HDR Imaging](https://mlsanity.com/paper/1806.07420/) (2018)

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

- [Real-time prediction of workplane illuminance distribution for daylight-linked controls using non-intrusive multimodal deep learning](https://mlsanity.com/paper/2512.14058/) (2025)
- [Dynamic Exposure Burst Image Restoration](https://mlsanity.com/paper/2603.21784/) (2026)
- [Neural Block-wise Auto-exposure for Single-Shot High Dynamic Range Imaging](https://mlsanity.com/paper/2610.18733/) (2026)

## Abstract (arXiv)

Mainstream high dynamic range imaging techniques typically rely on fusing multiple images captured with different exposure setups (shutter speed and ISO). A good balance between shutter speed and ISO is crucial for achieving high-quality HDR, as high ISO values introduce significant noise, while long shutter speeds can lead to noticeable motion blur. However, existing methods often overlook the complex interaction between shutter speed and ISO and fail to account for motion blur effects in dynamic scenes. In this work, we propose AdaptiveAE, a reinforcement learning-based method that optimizes the selection of shutter speed and ISO combinations to maximize HDR reconstruction quality in dynamic environments. AdaptiveAE integrates an image synthesis pipeline that incorporates motion blur and noise simulation into our training procedure, leveraging semantic information and exposure histograms. It can adaptively select optimal ISO and shutter speed sequences based on a user-defined exposure time budget, and find a better exposure schedule than traditional solutions. Experimental results across multiple datasets demonstrate that it achieves the state-of-the-art performance.