View in EDS

Enhancing temporal consistency in video super-resolution using optical flow-guided deep networks.

Saved in:
Bibliographic Details
Title: Enhancing temporal consistency in video super-resolution using optical flow-guided deep networks.
Authors: Aote, Shailendra S.1 (AUTHOR) shailendra.aote@gmail.com, Mahakalkar, Namrata2 (AUTHOR), Jaisinghani, Komal3 (AUTHOR), Pimpalshende, Anjusha4 (AUTHOR), Bongirwar, Vrushali5 (AUTHOR), Khade, Anindita6 (AUTHOR)
Source: Imaging Science Journal. Jul2026, Vol. 74 Issue 5, p501-515. 15p.
Subjects: Optical flow, Motion compensation (Signal processing), Deep learning, Image enhancement (Imaging systems), Image quality analysis
Abstract: This paper presents an optical flow-guided deep learning framework for video super-resolution (VSR) that enhances spatial detail and temporal consistency. While recent VSR methods incorporate temporal propagation, achieving stable motion alignment under occlusion and rapid motion remains challenging. The proposed approach employs RAFT-based optical flow to align adjacent low-resolution frames with a reference frame. These motion-compensated features are fused using a confidence-weighted attention mechanism and refined through a residual-in-residual dense block (RRDB) network to produce high-resolution outputs. A composite loss combining pixel-wise, perceptual, and temporal terms jointly optimizes spatial fidelity and motion coherence. Experiments on Vid4 and REDS benchmarks demonstrate that the proposed model attains higher PSNR and SSIM with lower LPIPS compared to state-of-the-art methods, while maintaining reduced computational complexity. Qualitative results confirm its ability to preserve textures, suppress artefacts, and ensure smooth frame transitions, making it suitable for real-world video enhancement applications. [ABSTRACT FROM AUTHOR]
Copyright of Imaging Science Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:This paper presents an optical flow-guided deep learning framework for video super-resolution (VSR) that enhances spatial detail and temporal consistency. While recent VSR methods incorporate temporal propagation, achieving stable motion alignment under occlusion and rapid motion remains challenging. The proposed approach employs RAFT-based optical flow to align adjacent low-resolution frames with a reference frame. These motion-compensated features are fused using a confidence-weighted attention mechanism and refined through a residual-in-residual dense block (RRDB) network to produce high-resolution outputs. A composite loss combining pixel-wise, perceptual, and temporal terms jointly optimizes spatial fidelity and motion coherence. Experiments on Vid4 and REDS benchmarks demonstrate that the proposed model attains higher PSNR and SSIM with lower LPIPS compared to state-of-the-art methods, while maintaining reduced computational complexity. Qualitative results confirm its ability to preserve textures, suppress artefacts, and ensure smooth frame transitions, making it suitable for real-world video enhancement applications. [ABSTRACT FROM AUTHOR]
ISSN:13682199
DOI:10.1080/13682199.2026.2624222