BS-RSC

Dataset Information
Modalities
Videos
Introduced
2022
License
MIT
Homepage

Overview

BS-RSC is a real-world rolling shutter (RS) correction dataset and a corresponding model to correct the RS frames in a distorted video. Real distorted videos with corresponding ground truth are recorded simultaneously via a well-designed beam-splitter-based acquisition system. BSRSC contains various motions of both camera and objects in dynamic scenes.

Variants: BS-RSC

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Rolling Shutter Correction DFRSC-3Frames Rolling Shutter Correction with Intermediate … 2024-04-09
Rolling Shutter Correction DFRSC-2Frames Rolling Shutter Correction with Intermediate … 2024-04-09
Rolling Shutter Correction QRSC-5Frames Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling … 2023-03-31
Rolling Shutter Correction AdaRSC-3Frames Learning Adaptive Warping for Real-World … 2022-04-29
Rolling Shutter Correction SUNet-2Frames SUNet: Symmetric Undistortion Network for … 2021-08-10
Rolling Shutter Correction JCD Towards Rolling Shutter Correction and … 2021-04-04

Research Papers

Recent papers with results on this dataset: