Memory-Augmented Non-Local Attention for Video Super-Resolution

• URL: http://arxiv.org/abs/2108.11048v1
• Date: Wed, 25 Aug 2021 05:12:14 GMT
• Title: Memory-Augmented Non-Local Attention for Video Super-Resolution
• Authors: Jiyang Yu, Jingen Liu, Liefeng Bo, Tao Mei
• Abstract summary: We propose a novel video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods predominantly leverage temporal neighbor frames to assist the super-resolution of the current frame. In contrast, we devise a cross-frame non-local attention mechanism that allows video super-resolution without frame alignment.
• Score: 61.55700315062226
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose a novel video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods predominantly leverage temporal neighbor frames to assist the super-resolution of the current frame. Those methods achieve limited performance as they suffer from the challenge in spatial frame alignment and the lack of useful information from similar LR neighbor frames. In contrast, we devise a cross-frame non-local attention mechanism that allows video super-resolution without frame alignment, leading to be more robust to large motions in the video. In addition, to acquire the information beyond neighbor frames, we design a novel memory-augmented attention module to memorize general video details during the super-resolution training. Experimental results indicate that our method can achieve superior performance on large motion videos comparing to the state-of-the-art methods without aligning frames. Our source code will be released.

Related papers

• Aggregating Long-term Sharp Features via Hybrid Transformers for Video Deblurring [76.54162653678871]
  We propose a video deblurring method that leverages both neighboring frames and present sharp frames using hybrid Transformers for feature aggregation. Our proposed method outperforms state-of-the-art video deblurring methods as well as event-driven video deblurring methods in terms of quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2023-09-13T16:12:11Z)
• SATVSR: Scenario Adaptive Transformer for Cross Scenarios Video Super-Resolution [0.0]
  Video Super-Resolution aims to recover sequences of high-resolution (HR) frames from low-resolution (LR) frames. Previous methods mainly utilize temporally adjacent frames to assist the reconstruction of target frames. We devise a novel adaptive scenario video super-resolution method. Specifically, we use optical flow to label the patches in each video frame, only calculate the attention of patches with the same label. Then select the most relevant label among them to supplement the spatial-temporal information of the target frame.
  arXiv  Detail & Related papers  (2022-11-16T06:30:13Z)
• VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution [75.79379734567604]
  We show that Video Implicit Neural Representation (VideoINR) can be decoded to videos of arbitrary spatial resolution and frame rate. We show that VideoINR achieves competitive performances with state-of-the-art STVSR methods on common up-sampling scales.
  arXiv  Detail & Related papers  (2022-06-09T17:45:49Z)
• 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)
• Video Super-Resolution with Long-Term Self-Exemplars [38.81851816697984]
  We propose a video super-resolution method with long-term cross-scale aggregation. Our model also consists of a multi-reference alignment module to fuse the features derived from similar patches. To evaluate our proposed method, we conduct extensive experiments on our collected CarCam dataset and the Open dataset.
  arXiv  Detail & Related papers  (2021-06-24T06:07:13Z)
• Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution [100.11355888909102]
  Space-time video super-resolution aims at generating a high-resolution (HR) slow-motion video from a low-resolution (LR) and low frame rate (LFR) video sequence. We present a one-stage space-time video super-resolution framework, which can directly reconstruct an HR slow-motion video sequence from an input LR and LFR video.
  arXiv  Detail & Related papers  (2021-04-15T17:59:23Z)
• Video Super-Resolution with Recurrent Structure-Detail Network [120.1149614834813]
  Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. We propose a novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame.
  arXiv  Detail & Related papers  (2020-08-02T11:01:19Z)
• Deep Slow Motion Video Reconstruction with Hybrid Imaging System [12.340049542098148]
  Current techniques increase the frame rate of standard videos through frame by assuming linear object motion which is not valid in challenging cases. We propose a two-stage deep learning system consisting of alignment and appearance estimation. We train our model on synthetically generated hybrid videos and show high-quality results on a variety of test scenes.
  arXiv  Detail & Related papers  (2020-02-27T14:18:12Z)

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.