Event-assisted 12-stop HDR Imaging of Dynamic Scene
Shi Guo, Zixuan Chen, Ziran Zhang, Yutian Chen, Gangwei Xu, Tianfan, Xue

TL;DR
This paper introduces a 12-stop HDR imaging method for dynamic scenes using a dual-camera system with an event camera and RGB camera, improving alignment and reducing artifacts in challenging lighting conditions.
Contribution
It presents a novel dual-camera HDR approach with event-based alignment, a diffusion-based fusion module, and the first dataset for 12-stop HDR with event signals, advancing dynamic scene HDR imaging.
Findings
Achieves state-of-the-art 12-stop HDR imaging in dynamic scenes.
Effectively reduces ghosting artifacts caused by motion.
Validates approach on both simulated and real-world data.
Abstract
High dynamic range (HDR) imaging is a crucial task in computational photography, which captures details across diverse lighting conditions. Traditional HDR fusion methods face limitations in dynamic scenes with extreme exposure differences, as aligning low dynamic range (LDR) frames becomes challenging due to motion and brightness variation. In this work, we propose a novel 12-stop HDR imaging approach for dynamic scenes, leveraging a dual-camera system with an event camera and an RGB camera. The event camera provides temporally dense, high dynamic range signals that improve alignment between LDR frames with large exposure differences, reducing ghosting artifacts caused by motion. Also, a real-world finetuning strategy is proposed to increase the generalization of alignment module on real-world events. Additionally, we introduce a diffusion-based fusion module that incorporates image…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques
MethodsDiffusion
