SEE: See Everything Every Time - Broader Light Range Image Enhancement via Events
Keywords: Event Camera, Image Brightness Enhancement, Brightness Adjustment Dataset
TL;DR: We develop a novel framework using event cameras and the SEE-0.6M dataset to enhance and adjust image brightness across a wide range of lighting conditions, enabling robust high dynamic range image restoration from day to night.
Abstract: Event cameras, with a high dynamic range exceeding $120dB$, significantly outperform traditional 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 adjust the brightness of images captured under broader lighting conditions.
To investigate this question, we first collected a new dataset, \textbf{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 broader 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.
Supplementary Material: zip
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 146
Loading