Dynamic Exposure Burst Image Restoration

2026-03-23

AI Summary

This work addresses a key limitation of conventional burst image restoration methods, which rely on fixed exposure settings and overlook the critical role of dynamically optimizing exposure time for reconstruction quality. To this end, we introduce Burst Auto-Exposure Network (BAENet), the first framework to integrate dynamic exposure control into burst restoration. BAENet adaptively predicts the optimal exposure time for each frame based on preview images, motion magnitude, and sensor gain. By leveraging a differentiable burst simulator and a three-stage end-to-end training strategy, our approach jointly optimizes exposure selection and image reconstruction. Extensive experiments demonstrate that BAENet significantly outperforms existing methods on both simulated and real camera systems, validating the effectiveness and practicality of the proposed dynamic exposure strategy.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Burst image restoration aims to reconstruct a high-quality image from burst images, which are typically captured using manually designed exposure settings. Although these exposure settings significantly influence the final restoration performance, the problem of finding optimal exposure settings has been overlooked. In this paper, we present Dynamic Exposure Burst Image Restoration (DEBIR), a novel burst image restoration pipeline that enhances restoration quality by dynamically predicting exposure times tailored to the shooting environment. In our pipeline, Burst Auto-Exposure Network (BAENet) estimates the optimal exposure time for each burst image based on a preview image, as well as motion magnitude and gain. Subsequently, a burst image restoration network reconstructs a high-quality image from burst images captured using these optimal exposure times. For training, we introduce a differentiable burst simulator and a three-stage training strategy. Our experiments demonstrate that our pipeline achieves state-of-the-art restoration quality. Furthermore, we validate the effectiveness of our approach on a real-world camera system, demonstrating its practicality.

Problem

• burst image restoration
• exposure settings
• auto-exposure
• image quality
• dynamic exposure

Innovation

• Dynamic Exposure
• Burst Image Restoration
• Auto-Exposure
• Differentiable Simulator
• Motion-Aware Imaging