BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation
and Alignment
- URL: http://arxiv.org/abs/2104.13371v1
- Date: Tue, 27 Apr 2021 17:58:31 GMT
- Title: BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation
and Alignment
- Authors: Kelvin C.K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
- Abstract summary: We show that by empowering recurrent framework with enhanced propagation and alignment, one can exploit video information more effectively.
Our model BasicVSR++ surpasses BasicVSR by 0.82 dB in PSNR with similar number of parameters.
BasicVSR++ generalizes well to other video restoration tasks such as compressed video enhancement.
- Score: 90.81396836308085
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A recurrent structure is a popular framework choice for the task of video
super-resolution. The state-of-the-art method BasicVSR adopts bidirectional
propagation with feature alignment to effectively exploit information from the
entire input video. In this study, we redesign BasicVSR by proposing
second-order grid propagation and flow-guided deformable alignment. We show
that by empowering the recurrent framework with the enhanced propagation and
alignment, one can exploit spatiotemporal information across misaligned video
frames more effectively. The new components lead to an improved performance
under a similar computational constraint. In particular, our model BasicVSR++
surpasses BasicVSR by 0.82 dB in PSNR with similar number of parameters. In
addition to video super-resolution, BasicVSR++ generalizes well to other video
restoration tasks such as compressed video enhancement. In NTIRE 2021,
BasicVSR++ obtains three champions and one runner-up in the Video
Super-Resolution and Compressed Video Enhancement Challenges. Codes and models
will be released to MMEditing.
Related papers
- FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution [68.77813885751308]
State-of-the-art (SOTA) compressed video super-resolution (CVSR) models face persistent challenges, including prolonged inference time, complex training pipelines, and reliance on auxiliary information.<n>We propose an efficient and scalable solution inspired by the structural and statistical similarities between hyperspectral images (HSI) and video data.<n>Our approach introduces a compression-driven dimensionality reduction strategy that reduces computational complexity, accelerates inference, and enhances the extraction of temporal information across frames.
arXiv Detail & Related papers (2025-06-13T07:59:52Z) - Super-Resolution Generative Adversarial Networks based Video Enhancement [0.40964539027092906]
This work introduces an enhanced approach to video super-resolution by extending ordinary Single-Image-SIS (SRGAN) structure to handle-versarial data.<n>A modified framework that incorporates 3D Non-Local Blocks is developed, which is enabling the model to capture relationships across both spatial and temporal dimensions.<n>Results show improved temporal coherence, sharper textures, and fewer visual artifacts compared to traditional single-image methods.
arXiv Detail & Related papers (2025-05-14T20:16:51Z) - Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors [80.92195378575671]
We describe a strong baseline for Arbitra-scale super-resolution (AVSR)
We then introduce ST-AVSR by equipping our baseline with a multi-scale structural and textural prior computed from the pre-trained VGG network.
Comprehensive experiments show that ST-AVSR significantly improves super-resolution quality, generalization ability, and inference speed over the state-of-theart.
arXiv Detail & Related papers (2024-07-13T15:27:39Z) - A Codec Information Assisted Framework for Efficient Compressed Video
Super-Resolution [15.690562510147766]
Video Super-Resolution (VSR) using recurrent neural network architecture is a promising solution due to its efficient modeling of long-range temporal dependencies.
We propose a Codec Information Assisted Framework (CIAF) to boost and accelerate recurrent VSR models for compressed videos.
arXiv Detail & Related papers (2022-10-15T08:48:29Z) - On the Generalization of BasicVSR++ to Video Deblurring and Denoising [98.99165593274304]
We extend BasicVSR++ to a generic framework for video restoration tasks.
In tasks where inputs and outputs possess identical spatial size, the input resolution is reduced by strided convolutions to maintain efficiency.
With only minimal changes from BasicVSR++, the proposed framework achieves compelling performance with great efficiency in various video restoration tasks.
arXiv Detail & Related papers (2022-04-11T17:59:56Z) - Learning Trajectory-Aware Transformer for Video Super-Resolution [50.49396123016185]
Video super-resolution aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts.
Existing approaches usually align and aggregate video frames from limited adjacent frames.
We propose a novel Transformer for Video Super-Resolution (TTVSR)
arXiv Detail & Related papers (2022-04-08T03:37:39Z) - BasicVSR: The Search for Essential Components in Video Super-Resolution
and Beyond [75.62146968824682]
Video super-resolution (VSR) approaches tend to have more components than the image counterparts.
We show a succinct pipeline, BasicVSR, that achieves appealing improvements in terms of speed and restoration quality.
arXiv Detail & Related papers (2020-12-03T18:56:14Z) - Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video
Super-Resolution [95.26202278535543]
A simple solution is to split it into two sub-tasks: video frame (VFI) and video super-resolution (VSR)
temporalsynthesis and spatial super-resolution are intra-related in this task.
We propose a one-stage space-time video super-resolution framework, which directly synthesizes an HR slow-motion video from an LFR, LR video.
arXiv Detail & Related papers (2020-02-26T16:59:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.