Seeing the Unseen: Zooming in the Dark with Event Cameras
Dachun Kai, Zeyu Xiao, Huyue Zhu, Jiaxiao Wang, Yueyi Zhang, Xiaoyan Sun

TL;DR
This paper introduces RetinexEVSR, a novel event-driven framework for low-light video super-resolution that effectively leverages event signals and Retinex priors to enhance detail recovery and reduce artifacts.
Contribution
RetinexEVSR is the first to integrate event data with Retinex-inspired priors for low-light video super-resolution, employing a bidirectional fusion strategy and illumination-guided enhancement modules.
Findings
Achieves state-of-the-art performance on three datasets.
Up to 2.95 dB gain on SDSD benchmark.
Reduces runtime by 65% compared to previous methods.
Abstract
This paper addresses low-light video super-resolution (LVSR), aiming to restore high-resolution videos from low-light, low-resolution (LR) inputs. Existing LVSR methods often struggle to recover fine details due to limited contrast and insufficient high-frequency information. To overcome these challenges, we present RetinexEVSR, the first event-driven LVSR framework that leverages high-contrast event signals and Retinex-inspired priors to enhance video quality under low-light scenarios. Unlike previous approaches that directly fuse degraded signals, RetinexEVSR introduces a novel bidirectional cross-modal fusion strategy to extract and integrate meaningful cues from noisy event data and degraded RGB frames. Specifically, an illumination-guided event enhancement module is designed to progressively refine event features using illumination maps derived from the Retinex model, thereby…
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
Taxonomy
TopicsAdvanced Memory and Neural Computing · Advanced Optical Sensing Technologies · Random lasers and scattering media
