# Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes Source: [Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:45:19.340Z Authors: Qiang Wen, Yue Wu, Qifeng Chen Published: 2023-02-12T13:47:26.000Z ## Abstract The waterdrops on windshields during driving can cause severe visual obstructions, which may lead to car accidents. Meanwhile, the waterdrops can also degrade the performance of a computer vision system in autonomous driving. To address these issues, we propose an attention-based framework that fuses the spatio-temporal representations from multiple frames to restore visual information occluded by waterdrops. Due to the lack of training data for video waterdrop removal, we propose a large-scale synthetic dataset with simulated waterdrops in complex driving scenes on rainy days. To improve the generality of our proposed method, we adopt a cross-modality training strategy that combines synthetic videos and real-world images. Extensive experiments show that our proposed method can generalize well and achieve the best waterdrop removal performance in complex real-world driving scenes. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Video waterdrop removal on Real driving scenes](): Video Waterdrop Removal; Real driving scenes; User Preference: 77.84. - [Video Waterdrop Removal on Proposed Synthetic Video Waterdrop Dataset (test)](): Video Waterdrop Removal; Proposed Synthetic Video Waterdrop Dataset (test); PSNR: 29.5789. - [Video Deraining on LWDDS](): Video Deraining; LWDDS; PSNR: 30.72. ## Original sources and implementation [Original paper]() [PDF]()