SEE: See Everything Every Time -- Adaptive Brightness Adjustment for Broad Light Range Images via Events

2025-02-28

AI Summary

This work addresses the challenging problem of adaptive image brightness adjustment across a wide illumination spectrum—from low-light to overexposed conditions. We present the first systematic investigation into leveraging event camera high-dynamic-range (HDR) data for full-spectrum image enhancement. Our method introduces an event-driven, pixel-level dynamic range recalibration framework: it models event streams as a luminance prior dictionary and employs a cross-modal cross-attention architecture to enable luminance-prompted decoding and broad-illumination representation (BLR) learning. To support this, we introduce SEE-600K—the first large-scale, multi-illumination event–image paired dataset. Experiments demonstrate that our approach achieves robust, wide-illumination-range enhancement on SEE-600K, enabling fine-grained brightness control while preserving state-of-the-art low-light enhancement performance. The code and dataset are publicly released.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Data transparency and provenance

Abstract

Event cameras, with a high dynamic range exceeding $120dB$, significantly outperform traditional embedded cameras, robustly recording detailed changing information under various lighting conditions, including both low- and high-light situations. However, recent research on utilizing event data has primarily focused on low-light image enhancement, neglecting image enhancement and brightness adjustment across a broader range of lighting conditions, such as normal or high illumination. Based on this, we propose a novel research question: how to employ events to enhance and adaptively adjust the brightness of images captured under broad lighting conditions? To investigate this question, we first collected a new dataset, SEE-600K, consisting of 610,126 images and corresponding events across 202 scenarios, each featuring an average of four lighting conditions with over a 1000-fold variation in illumination. Subsequently, we propose a framework that effectively utilizes events to smoothly adjust image brightness through the use of prompts. Our framework captures color through sensor patterns, uses cross-attention to model events as a brightness dictionary, and adjusts the image's dynamic range to form a broad light-range representation (BLR), which is then decoded at the pixel level based on the brightness prompt. Experimental results demonstrate that our method not only performs well on the low-light enhancement dataset but also shows robust performance on broader light-range image enhancement using the SEE-600K dataset. Additionally, our approach enables pixel-level brightness adjustment, providing flexibility for post-processing and inspiring more imaging applications. The dataset and source code are publicly available at:https://github.com/yunfanLu/SEE.

Problem

• Enhance images across broad lighting conditions using event data.
• Develop adaptive brightness adjustment for high dynamic range images.
• Create a framework for pixel-level brightness adjustment and post-processing.

Innovation

• Uses event cameras for broad light range imaging.
• Develops SEE-600K dataset with varied lighting conditions.
• Implements brightness adjustment via cross-attention and prompts.