Video Super-resolution with Temporal Group Attention
Not on the map. Why?
Abstract (arXiv)
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate temporal information in a hierarchical way. The input sequence is divided into several groups, with each one corresponding to a kind of frame rate. These groups provide complementary information to recover missing details in the reference frame, which is further integrated with an attention module and a deep intra-group fusion module. In addition, a fast spatial alignment is proposed to handle videos with large motion. Extensive results demonstrate the capability of the proposed model in handling videos with various motion. It achieves favorable performance against state-of-the-art methods on several benchmark datasets.
Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jul 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 21; 2022: 24; 2023: 15; 2024: 8; 2025: 11; 2026: 2.
81 papers.
Sort:
By area:
- 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
- 2022VRT: A Video Restoration Transformercited by 219
- 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
- 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
- 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
- 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
- 2021Video Super-Resolution Transformercited by 120
- 2024VEnhancer: Generative Space-Time Enhancement for Video Generationcited by 64
- 2022Learning Trajectory-Aware Transformer for Video Super-Resolutioncited by 61
- 2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
- 2021Multi-Target Domain Adaptation with Collaborative Consistency Learningcited by 43
- 2022Low-Light Video Enhancement with Synthetic Event Guidancecited by 33
38 more
- 2023Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolutioncited by 33
- 2021Omniscient Video Super-Resolutioncited by 30
- 2022Mitigating Artifacts in Real-World Video Super-Resolution Modelscited by 29
- 2024Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attentioncited by 29
- 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurringcited by 28
- 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolutioncited by 23
- 2022Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modelingcited by 20
- 2021FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolutioncited by 19
- 2021Self-Conditioned Probabilistic Learning of Video Rescalingcited by 19
- 2023Local-Global Temporal Difference Learning for Satellite Video Super-Resolutioncited by 19
- 2021Learning for Unconstrained Space-Time Video Super-Resolutioncited by 18
- 2021Memory-Augmented Non-Local Attention for Video Super-Resolutioncited by 17
- 2022Temporal Consistency Learning of inter-frames for Video Super-Resolutioncited by 16
- 2021NTIRE 2021 Challenge on Video Super-Resolutioncited by 15
- 2022Self-Supervised Deep Blind Video Super-Resolutioncited by 15
- 2022Structured Sparsity Learning for Efficient Video Super-Resolutioncited by 14
- 2024Learning Truncated Causal History Model for Video Restorationcited by 13
- 2025Show and Polish: Reference-Guided Identity Preservation in Face Video Restorationcited by 12
- 2022A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shiftcited by 10
- 2021Triple-level Model Inferred Collaborative Network Architecture for Video Derainingcited by 9
- 2022Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolutioncited by 9
- 2021Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolutioncited by 8
- 2022Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolutioncited by 8
- 2022Reference-based Image and Video Super-Resolution via C2-Matchingcited by 8
- 2023Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolutioncited by 8
- 2023TMP: Temporal Motion Propagation for Online Video Super-Resolutioncited by 8
- 2021SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformerscited by 7
- 2021Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscalingcited by 6
- 2021Stable Long-Term Recurrent Video Super-Resolutioncited by 6
- 2022STDAN: Deformable Attention Network for Space-Time Video Super-Resolutioncited by 6
- 2024Deep Blind Super-Resolution for Satellite Videocited by 6
- 2024HR-INR: Continuous Space-Time Video Super-Resolution via Event Cameracited by 6
- 2025A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimulicited by 6
- 2022Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metriccited by 5
- 2025Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolutioncited by 5
- 2025A Survey of Deep Learning Video Super-Resolutioncited by 5
- 2026SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagationcited by 5
- 2022Optical Flow for Video Super-Resolution: A Surveycited by 4
50 most cited of 81 All 81 (JSON)
- 2026SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation17 Mar 2026
- 2026Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm9 Feb 2026
- 2025STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution24 Nov 2025
- 2025Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events4 Oct 2025
- 2025Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects19 Sep 2025
- 2025Audio-Assisted Face Video Restoration with Temporal and Identity Complementary Learning6 Aug 2025
- 2025Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration14 Jul 2025
- 2025FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution13 Jun 2025
- 2025Omnidirectional Video Super-Resolution using Deep Learning3 Jun 2025
- 2025A Survey of Deep Learning Video Super-Resolution3 Jun 2025
- 2025Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution1 Jun 2025
- 2025Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution4 May 2025
38 more
- 2025A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli20 Mar 2025
- 2024Towards Degradation-Robust Reconstruction in Generalizable NeRF18 Nov 2024
- 2024Learning Truncated Causal History Model for Video Restoration4 Oct 2024
- 2024VEnhancer: Generative Space-Time Enhancement for Video Generation10 Jul 2024
- 2024HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera22 May 2024
- 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution25 Mar 2024
- 2024Deep Blind Super-Resolution for Satellite Video13 Jan 2024
- 2024Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention12 Jan 2024
- 2024FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring8 Jan 2024
- 2023Toward Accurate and Temporally Consistent Video Restoration from Raw Data25 Dec 2023
- 2023ViStripformer: A Token-Efficient Transformer for Versatile Video Restoration22 Dec 2023
- 2023TMP: Temporal Motion Propagation for Online Video Super-Resolution15 Dec 2023
- 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution11 Dec 2023
- 2023Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution26 Oct 2023
- 2023Video Super-Resolution Using a Grouped Residual in Residual Network17 Oct 2023
- 2023A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution25 Sep 2023
- 2023Cross-Consistent Deep Unfolding Network for Adaptive All-In-One Video Restoration4 Sep 2023
- 2023Real-World Video for Zoom Enhancement based on Spatio-Temporal Coupling24 Jun 2023
- 2023RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection22 Jun 2023
- 2023EgoVSR: Towards High-Quality Egocentric Video Super-Resolution24 May 2023
- 2023Local-Global Temporal Difference Learning for Satellite Video Super-Resolution10 Apr 2023
- 2023Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution24 Mar 2023
- 2023ReBotNet: Fast Real-time Video Enhancement23 Mar 2023
- 2023Learning Physical-Spatio-Temporal Features for Video Shadow Removal16 Mar 2023
- 2022Cross-Resolution Flow Propagation for Foveated Video Super-Resolution27 Dec 2022
- 2022Reference-based Image and Video Super-Resolution via C2-Matching19 Dec 2022
- 2022Mitigating Artifacts in Real-World Video Super-Resolution Models14 Dec 2022
- 2022Temporal Consistency Learning of inter-frames for Video Super-Resolution3 Nov 2022
- 2022Low-Light Video Enhancement with Synthetic Event Guidance23 Aug 2022
- 2022Restoration of User Videos Shared on Social Media18 Aug 2022
- 2022Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization18 Jul 2022
- 2022Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution5 Jul 2022
- 2022Structured Sparsity Learning for Efficient Video Super-Resolution15 Jun 2022
- 2022Recurrent Video Restoration Transformer with Guided Deformable Attention5 Jun 2022
- 2022Efficient Multi-Purpose Cross-Attention Based Image Alignment Block for Edge Devices1 Jun 2022
- 2022Accelerating the Training of Video Super-Resolution Models10 May 2022
- 2022Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling14 Apr 2022
- 2022Learning Trajectory-Aware Transformer for Video Super-Resolution8 Apr 2022
50 newest of 81 All 81 (JSON)
- 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
- 2024VEnhancer: Generative Space-Time Enhancement for Video Generationcited by 64
- 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolutioncited by 23
- 2025Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolutioncited by 5
- 2025STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolutioncited by 0
- 2025STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution24 Nov 2025
- 2025Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution1 Jun 2025
- 2024VEnhancer: Generative Space-Time Enhancement for Video Generation10 Jul 2024
- 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution25 Mar 2024
- 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution11 Dec 2023
- 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
- 2022VRT: A Video Restoration Transformercited by 219
- 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
- 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
- 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
- 2021Video Super-Resolution Transformercited by 120
- 2022Learning Trajectory-Aware Transformer for Video Super-Resolutioncited by 61
- 2022TAPE: Task-Agnostic Prior Embedding for Image Restorationcited by 54
- 2021Multi-Target Domain Adaptation with Collaborative Consistency Learningcited by 43
- 2022Low-Light Video Enhancement with Synthetic Event Guidancecited by 33
- 2023Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolutioncited by 33
- 2021Omniscient Video Super-Resolutioncited by 30
12 most cited of 76 All 76 (JSON)
- 2026SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation17 Mar 2026
- 2026Low-Light Video Enhancement with An Effective Spatial-Temporal Decomposition Paradigm9 Feb 2026
- 2025Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events4 Oct 2025
- 2025Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects19 Sep 2025
- 2025Audio-Assisted Face Video Restoration with Temporal and Identity Complementary Learning6 Aug 2025
- 2025Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration14 Jul 2025
- 2025FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution13 Jun 2025
- 2025Omnidirectional Video Super-Resolution using Deep Learning3 Jun 2025
- 2025A Survey of Deep Learning Video Super-Resolution3 Jun 2025
- 2025Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution4 May 2025
- 2025A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli20 Mar 2025
- 2024Towards Degradation-Robust Reconstruction in Generalizable NeRF18 Nov 2024
12 newest of 76 All 76 (JSON)