DM-VSR: Depth-Aware Diffusion Models With Adaptive Modulation for Video Super-Resolution
IEEE Transactions on Broadcasting · 2026-03 · 72 (1) · 329-344
DOI: 10.1109/tbc.2025.3637713 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Broadcasting, 2026-03. Verfasst von Linlin Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Zhejiang Province Key Research and Development Program, Zhejiang Province Collaborative Innovation Program for High-Quality Manufacturing Development.
Abstract (Originalsprache)
Video Super-Resolution (VSR) is essential for enhancing the quality of low-resolution (LR) videos in practical applications. Recent studies have explored diffusion models (DMs) for VSR due to their ability to generate realistic details. However, existing methods overlook spatiotemporal object-scale variations and dynamic control demands during denoising. This leads to visual distortion and quality degradation, severely limiting its practical applications. To address these limitations, we propose DM-VSR, a novel DM-based framework that incorporates depth-aware guidance and adaptive modulation for precise content reconstruction. Specifically, a Depth-aware Multimodal Fusion (DMF) module integrates depth maps, LR inputs, and flow-warped frames to provide unified depth-aware guidance. A Timestep Adaptive Modulation (TAM) module dynamically adjusts the control feature injection according to demand at each denoising step. Additionally, a Dynamic Consistency Loss (DCL) is introduced to align training objectives with the evolving semantic focus. Extensive experiments on the REDS4 and Vid4 benchmarks demonstrate that DM-VSR achieves competitive performance, surpassing state-of-the-art methods in both perceptual quality and temporal consistency. Moreover, DM-VSR generates more visually realistic results, emphasizing its effectiveness in real-world applications. The code will be released at https://github.com/aigcvsr/DM-VSR
Förderung
- Zhejiang Province Key Research and Development Program
- Zhejiang Province Collaborative Innovation Program for High-Quality Manufacturing Development
Zitieren
APA
Liu, L., Wang, Y., Wang, Y., Xu, Z., Tang, J., & Ding, Y. (2026). DM-VSR: Depth-Aware Diffusion Models With Adaptive Modulation for Video Super-Resolution. IEEE Transactions on Broadcasting, 72(1), 329-344. https://doi.org/10.1109/tbc.2025.3637713
Vancouver
Liu L, Wang Y, Wang Y, Xu Z, Tang J, Ding Y. DM-VSR: Depth-Aware Diffusion Models With Adaptive Modulation for Video Super-Resolution. IEEE Transactions on Broadcasting. 2026;72(1):329-344. doi:10.1109/tbc.2025.3637713
BibTeX
@article{Liu2026,
author = {Liu, Linlin and Wang, Yifan and Wang, Yize and Xu, Zhen and Tang, Jun and Ding, Yong},
title = {DM-VSR: Depth-Aware Diffusion Models With Adaptive Modulation for Video Super-Resolution},
journal = {IEEE Transactions on Broadcasting},
year = {2026},
volume = {72},
number = {1},
pages = {329--344},
doi = {10.1109/tbc.2025.3637713}
}
EUVIMED