SelfDRSC++: Self-supervised dual reversed rolling shutter correction via video interpolation

Publication Type

Journal Article

Publication Date

12-2026

Abstract

Modern consumer cameras often use rolling shutter, capturing scenes row-by-row and causing distortion in dynamic scenes. Existing correction methods rely on supervised learning with high-frame-rate global shutter images as ground truth. We propose SelfDRSC++, a self-supervised framework for RS distortion correction from simultaneously captured top-to-bottom and bottom-to-top RS images. A lightweight network with a bidirectional correlation matching block jointly optimizes optical flows and corrected RS features, improving performance with fewer parameters. A self-supervised strategy enforces a physically constrained RS–GS–RS cycle between input and reconstructed dual reversed RS images. RS reconstruction is formulated as a specialized video frame interpolation task, enabling feasible one-stage training. Extensive experiments on synthetic and real-world data show that SelfDRSC++ achieves competitive quantitative performance, improves perceptual quality, and produces high-frame-rate GS sequences with better temporal consistency.

Keywords

Rolling shutter correction, Self-supervised learning, Video interpolation

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Publication

Pattern Recognition

Volume

180

First Page

1

Last Page

13

ISSN

0031-3203

Identifier

10.1016/j.patcog.2026.114636

Publisher

Elsevier

Additional URL

https://doi.org/10.1016/j.patcog.2026.114636

This document is currently not available here.

Share

COinS