Saved in:
Bibliographic Details
Main Authors: Tang, Qi, Zhao, Yao, Liu, Meiqin, Yao, Chao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.05799
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914991749201920
author Tang, Qi
Zhao, Yao
Liu, Meiqin
Yao, Chao
author_facet Tang, Qi
Zhao, Yao
Liu, Meiqin
Yao, Chao
contents Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level alignment is ineffective for diffusion-processed frames because of iterative disruptions. To overcome this, we introduce SeeClear--a novel VSR framework leveraging conditional video generation, orchestrated by instance-centric and channel-wise semantic controls. This framework integrates a Semantic Distiller and a Pixel Condenser, which synergize to extract and upscale semantic details from low-resolution frames. The Instance-Centric Alignment Module (InCAM) utilizes video-clip-wise tokens to dynamically relate pixels within and across frames, enhancing coherency. Additionally, the Channel-wise Texture Aggregation Memory (CaTeGory) infuses extrinsic knowledge, capitalizing on long-standing semantic textures. Our method also innovates the blurring diffusion process with the ResShift mechanism, finely balancing between sharpness and diffusion effects. Comprehensive experiments confirm our framework's advantage over state-of-the-art diffusion-based VSR techniques. The code is available: https://github.com/Tang1705/SeeClear-NeurIPS24.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05799
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
Tang, Qi
Zhao, Yao
Liu, Meiqin
Yao, Chao
Computer Vision and Pattern Recognition
Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level alignment is ineffective for diffusion-processed frames because of iterative disruptions. To overcome this, we introduce SeeClear--a novel VSR framework leveraging conditional video generation, orchestrated by instance-centric and channel-wise semantic controls. This framework integrates a Semantic Distiller and a Pixel Condenser, which synergize to extract and upscale semantic details from low-resolution frames. The Instance-Centric Alignment Module (InCAM) utilizes video-clip-wise tokens to dynamically relate pixels within and across frames, enhancing coherency. Additionally, the Channel-wise Texture Aggregation Memory (CaTeGory) infuses extrinsic knowledge, capitalizing on long-standing semantic textures. Our method also innovates the blurring diffusion process with the ResShift mechanism, finely balancing between sharpness and diffusion effects. Comprehensive experiments confirm our framework's advantage over state-of-the-art diffusion-based VSR techniques. The code is available: https://github.com/Tang1705/SeeClear-NeurIPS24.
title SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.05799