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

2025-08-19

AI Summary

Existing HDR imaging methods for dynamic scenes suffer from suboptimal joint shutter speed–ISO optimization and inadequate modeling of motion blur and sensor noise. To address these limitations, this paper proposes a reinforcement learning–based adaptive exposure strategy. It is the first to formulate shutter speed and ISO selection as a unified sequential decision-making problem within a single optimization framework. The policy network integrates semantic segmentation maps and exposure histograms as multimodal inputs, while motion blur and sensor noise are explicitly modeled within the image synthesis pipeline to enable end-to-end differentiable training. Evaluated on multiple dynamic HDR benchmarks, the method significantly outperforms state-of-the-art approaches in suppressing motion artifacts and noise while improving HDR reconstruction fidelity. Quantitatively, it achieves new state-of-the-art performance in both PSNR and LPIPS metrics.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• Optimizing shutter speed and ISO for HDR imaging
• Reducing motion blur and noise in dynamic scenes
• Adaptive exposure selection under time constraints

Innovation

• Reinforcement learning optimizes ISO and shutter speed
• Integrates motion blur and noise simulation training
• Adaptively selects exposure sequences within time budget