One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Yujing, Sun, Lingchen, Liu, Shuaizheng, Wu, Rongyuan, Zhang, Zhengqiang, Zhang, Lei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908605292216320
author Sun, Yujing
Sun, Lingchen
Liu, Shuaizheng
Wu, Rongyuan
Zhang, Zhengqiang
Zhang, Lei
author_facet Sun, Yujing
Sun, Lingchen
Liu, Shuaizheng
Wu, Rongyuan
Zhang, Zhengqiang
Zhang, Lei
contents It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
Sun, Yujing
Sun, Lingchen
Liu, Shuaizheng
Wu, Rongyuan
Zhang, Zhengqiang
Zhang, Lei
Computer Vision and Pattern Recognition
Artificial Intelligence
It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL.
title One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.15591