add iccv21 sr papers

farewell-lc · Oct 22, 2021 · 9365546 · 9365546
1 parent c8f7d86
commit 9365546
Showing 1 changed file with 25 additions and 13 deletions.
diff --git a/README.md b/README.md
@@ -32,21 +32,17 @@ More years papers, plase check Quick navigation
 |Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution        | TrilevelNAS            | [arxiv](https://arxiv.org/pdf/2101.06658.pdf)            | -              | Trilevel Architecture Search Space      |
 |SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices                  | SplitSR                | [arxiv](https://arxiv.org/pdf/2101.07996.pdf)            | -              | lightweight,on Mobile Devices      |
 |Learning for Unconstrained Space-Time Video Super-Resolution                           | USTVSRNet              | [arxiv](https://arxiv.org/pdf/2102.13011.pdf)            | -              | ***VSR***, Unconstrained video super-resolution,general-ized  pixelshuffle  layer.     |
-|ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic| ClassSR            | [cvpr21](https://arxiv.org/pdf/2103.04039.pdf)           | [code](https://github.com/Xiangtaokong/ClassSR)         | classification，lightweight | 
-|Learning Frequency-aware Dynamic Network for Efficient Super-Resolution                | FADN                   | [arxiv](https://arxiv.org/pdf/2103.08357.pdf)            | -              |  Efficient SR，DCT，Mask Predictor，dynamic resblocks，frequency mask loss|
+|ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic| ClassSR            | [cvpr21](https://arxiv.org/pdf/2103.04039.pdf)           | [code](https://github.com/Xiangtaokong/ClassSR)         | classification，lightweight |
 |Collapsible Linear Blocks for Super-Efficient Super Resolution                         | SESR                   | [arxiv](https://arxiv.org/pdf/2103.09404.pdf)            | -              |  Super-Efficient SR, overparameterization|
 |Self-Supervised Adaptation for Video Super-Resolution                                  | Adapted VSR            | [arxiv](https://arxiv.org/pdf/2103.10081.pdf)            | -              |  ***VSR***, Self-Supervised Adaptationn|
 |Generic Perceptual Loss for Modeling Structured Output Dependencies                    | Generic Perceptual Loss| [cvpr21](https://arxiv.org/pdf/2103.10571.pdf)           | -              |  Random VGG w/o pretrianed, work at semantic segmentation, depthestimation  and  instance  segmentation|
 |Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling| U3D-RDN           | [AAAI21](https://arxiv.org/pdf/2103.11744.pdf)           | -              |  ***VSR***, Dual Subnet, Multi-stage Communicated Up-sampling|
 |UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution| UltraSR         | [arxiv](https://arxiv.org/pdf/2103.12716.pdf)            | -              |  Implicit Image Function Based, Arbitrary-Scale|
-|Designing a Practical Degradation Model for Deep Blind Image Super-Resolution          | BSRNet/BSRGAN          | [arxiv](https://arxiv.org/pdf/2103.14006.pdf)            | -              |  randomly shuffled blur, downsampling and noise degradations for degradation model |
 |D2C-SR: A Divergence to Convergence Approach for Image Super-Resolution                | D2C-SR                 | [arxiv](https://arxiv.org/pdf/2103.14373.pdf)            | -              |  RealSR， divergence stage with a triple loss ，convergence stage|
 |Training a Better Loss Function for Image Restoration                                  | MDF loss               | [arxiv](https://arxiv.org/pdf/2103.14616.pdf)            | [code](https://github.com/gfxdisp/mdf)              |  Multi-Scale Discriminative Feature loss|
 |Transitive Learning: Exploring the Transitivity of Degradations for Blind Super-Resolution| TLSR                | [arxiv](https://arxiv.org/pdf/2103.15290.pdf)            | [code](https://github.com/YuanfeiHuang/TLSR)        | Blind SR， Transitive Learning   |
-|Omniscient Video Super-Resolution                                                      | OVSR                   | [arxiv](https://arxiv.org/pdf/2103.15683.pdf)            | -              | ***VSR***， new framework， precursor net and successor net  |
 |Best-Buddy GANs for Highly Detailed Image Super-Resolution                             | Beby-GAN               | [arxiv](https://arxiv.org/pdf/2103.15295.pdf)            | [code](https://github.com/Jia-Research-Lab/Simple-SR)  |relaxing the immutable one-to-one constraint, Best-Buddy Loss  |
 |Flow-based Kernel Prior with Application to Blind Super-Resolution                     | FKP                    | [cvpr21](https://arxiv.org/pdf/2103.15977.pdf)           | [code](https://github.com/JingyunLiang/FKP)            |Blind SR, flow-based kernel prio|
-|Efficient Video Compression via Content-Adaptive Super-Resolution                      | SRVC                   | [arxiv](https://arxiv.org/pdf/2104.02322.pdf)            | -            |Video Compression， Adaptive Conv|
 |Conditional Meta-Network for Blind Super-Resolution with Multiple Degradations         | CMDSR                  | [arxiv](https://arxiv.org/pdf/2104.03926.pdf)            | -            |Blind SR, Conditional Meta-Network|
 |Image Super-Resolution via Iterative Refinement                                        | SR3                    | [arxiv](https://arxiv.org/pdf/2104.07636.pdf)            | -            |Repeated Refinement, better than  SOTA GAN|
 |BAM: A Lightweight and Efficient Balanced Attention Mechanism for Single Image Super Resolution| BAM            | [arxiv](https://arxiv.org/pdf/2104.07566.pdf)            | [code](https://github.com/dandingbudanding/BAM_A_lightweight_but_efficient_Balanced_attention_mechanism_for_super_resolution)            |balanced Attention Mechanism |
@@ -65,7 +61,6 @@ More years papers, plase check Quick navigation
 |End-to-end Alternating Optimization for Blind Super Resolution   | DAN      | [arxiv](https://arxiv.org/pdf/2105.06878.pdf)            |[code](https://github.com/greatlog/DAN)  |  Blind SR, Restorer and Estimator Alternating Optimization  |
 |Anchor-based Plain Net for Mobile Image Super-Resolution   | ABPN      | [arxiv](https://arxiv.org/pdf/2105.09750.pdf)            |[code](https://github.com/NJU-Jet/SR_Mobile_Quantization)  |  MAI2021, mobile device SISR, INT8 Quantization  |
 |Extremely Lightweight Quantization RobustReal-Time Single-Image Super Resolution for Mobile Devices   | XLSR      | [arxiv](https://arxiv.org/pdf/2105.10288.pdf)            |-  |  MAI2021, mobile device SISR Winner, INT8 Quantization  |
-|Fourier Space Losses for Efficient Perceptual Image Super-Resolution   | -      | [arxiv](https://arxiv.org/pdf/2105.09750.pdf)            |-  |   Fourier space supervision loss  |
 |Robust Reference-based Super-Resolution via C2-Matching   | C2-Matching      | [arxiv](https://arxiv.org/pdf/2105.09750.pdf)            |[code](https://github.com/yumingj/C2-Matching)  |   RefSR, ransformation gap, contrastive correspondence network, resolution gap, teacher-student  correlation  distillation  |
 |MASA-SR: Matching Acceleration and Spatial Adaptation forReference-Based Image Super-Resolution   | MASA-SR      | [cvpr21](https://arxiv.org/pdf/2106.02299.pdf)            |[code](https://github.com/dvlab-research/MASA-SR)  |   RefSR, Match & Extraction Module , Spatial Adaptation Module|
 |Noise Conditional Flow Model for Learning the Super-Resolution Space   | NCSR      | [arxiv](https://arxiv.org/pdf/2106.04428.pdf)            |[code](https://github.com/younggeun-kim/NCSR)  |   better than GAN-based model，Flow-based， noise conditional layer |
@@ -92,16 +87,33 @@ More years papers, plase check Quick navigation
 |Deep Burst Super-Resolution                                                            | BurstSR                | [cvpr21](https://openaccess.thecvf.com/content/CVPR2021/papers/Bhat_Deep_Burst_Super-Resolution_CVPR_2021_paper.pdf)            | -              | multi-frame sr, new BurstSR dataset      |
 |Pre-Trained Image Processing Transformer |IPT          | [cvpr21](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Pre-Trained_Image_Processing_Transformer_CVPR_2021_paper.pdf)  |[code](https://github.com/huawei-noah/Pretrained-IPT) | Pre-Trained Image Processing Transformer, Imagenet pretrained, dramatically improve performance  |
 |Blind Image Super-Resolution via ContrastiveRepresentation Learning   | CRL-SR       | [arxiv](https://arxiv.org/pdf/2107.00708.pdf)     |-  | blind SR, contrastive decoupling encoding， contrastive feature refinement   |
-|Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution   | MANet       | [iccv21](https://arxiv.org/pdf/2108.05302.pdf)     |[code](https://github.com/JingyunLiang/MANet)  | blind SR, spatially variant and invariant kernel, mutual affine network   |
-|Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling   | HCFlow       | [iccv21](https://arxiv.org/pdf/2108.05301.pdf)     |[code](https://github.com/JingyunLiang/HCFlow)  | SR/Rescale, learns a bijective mapping    |
 |End-to-End Adaptive Monte Carlo Denoising and Super-Resolution   | -       | [arxiv](https://arxiv.org/pdf/2108.06915.pdf)     |-  | Monte Carlo path tracing    |
-|Deep Reparametrization of Multi-Frame Super-Resolution and Denoising   | -       | [iccv21](https://arxiv.org/pdf/2108.08286.pdf)     |-  | Multi-Frame，deep reparametrization of the classical MAP objective    |
 |SwinIR: Image Restoration Using Swin Transformer   | SwinIR       | [arxiv](https://arxiv.org/pdf/2108.10257.pdf)     |[code](https://github.com/JingyunLiang/SwinIR)  |SISR， Swin Transformer， SOTA    |
 |edge–SR: Super–Resolution For The Masses   | eSR       | [arxiv](https://arxiv.org/pdf/2108.10335.pdf)     |-  |SISR， Edge device SR，one–layer architectures use interpretable mechanisms， Filling the gap between classic and deep learning architectures |
 |Memory-Augmented Non-Local Attention for Video Super-Resolution   | CSNLN       | [arxiv](https://arxiv.org/pdf/2108.11048.pdf)     |-  |***VSR***， without frame alignment， memory-augmented attention module |
-|Attention-based Multi-Reference Learning for Image Super-Resolution   | AMRSR       | [arxiv](https://arxiv.org/pdf/2108.13697.pdf)     |[code](https://marcopesavento.github.io/AMRSR)  |RefSR， without frame alignment， Hierarchical Attention-based Similarity |
 |Simple and Efficient Unpaired Real-world Super-Resolution using Image Statistics   | -       | [arxiv](https://arxiv.org/pdf/2109.09071.pdf)     |-  |unpair SR,variance matching |
-|Dual-Camera Super-Resolution with Aligned Attention Modules   | -       | [iccv21](https://arxiv.org/pdf/2109.01349.pdf)     |[code](https://tengfei-wang.github.io/Dual-Camera-SR/index.html)  | oral, dual camera SR, RefSR,self-supervised domain adaptation strategy    |
-|Learning A Single Network for Scale-Arbitrary Super-Resolution   | arbSR       | [iccv21](https://arxiv.org/pdf/2004.03791.pdf)     |[code](https://github.com/LongguangWang/ArbSR)  | SISR， scale-arbitrary SR   |
 |Improving Super-Resolution Performance using Meta-Attention Layers   | -       | [SPL](https://ieeexplore.ieee.org/document/9552573)     |[code](https://github.com/um-dsrg/Super-Resolution-Meta-Attention-Networks)  | SISR， meta-attention   |
-|EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation   | -       | [arxiv](https://arxiv.org/pdf/2110.07797.pdf)     |[code](https://github.com/IndigoPurple/EFENet)  | RefVSR， Enhanced Flow Estimation   |
+|EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation   | EFENet | [arxiv](https://arxiv.org/pdf/2110.07797.pdf)     |[code](https://github.com/IndigoPurple/EFENet)  | RefVSR， Enhanced Flow Estimation   |
+|Learning A Single Network for Scale-Arbitrary Super-Resolution | arbSR | [iccv21](https://arxiv.org/pdf/2004.03791.pdf) |[code](https://github.com/LongguangWang/ArbSR) | SISR， scale-arbitrary SR |
+|Dual-Camera Super-Resolution with Aligned Attention Modules | - | [iccv21](https://arxiv.org/pdf/2109.01349.pdf) |[code](https://tengfei-wang.github.io/Dual-Camera-SR/index.html) | oral, dual camera SR, RefSR,self-supervised domain adaptation strategy |
+|Learning Frequency-aware Dynamic Network for Efficient Super-Resolution | FADN | [iccv21](https://arxiv.org/pdf/2103.08357.pdf) |- | Efficient SR，DCT，Mask Predictor，dynamic resblocks，frequency mask loss |
+|Designing a Practical Degradation Model for Deep Blind Image Super-Resolution | BSRNet/BSRGAN | [iccv21](https://arxiv.org/pdf/2103.14006.pdf) |- | randomly shuffled blur, downsampling and noise degradations for degradation model |
+|Fourier Space Losses for Efficient Perceptual Image Super-Resolution | - | [iccv21](https://arxiv.org/pdf/2105.09750.pdf) |- | Fourier space supervision loss |
+|Omniscient Video Super-Resolution | OVSR | [iccv21](https://arxiv.org/pdf/2103.15683.pdf) |- | ***VSR***， new framework， precursor net and successor net |
+|Efficient Video Compression via Content-Adaptive Super-Resolution | SRVC | [iccv21](https://arxiv.org/pdf/2104.02322.pdf) |- | Video Compression， Adaptive Conv |
+|Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution | MANet | [iccv21](https://arxiv.org/pdf/2108.05302.pdf) |[code](https://github.com/JingyunLiang/MANet) | blind SR, spatially variant and invariant kernel, mutual affine network |
+|Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling | HCFlow | [iccv21](https://arxiv.org/pdf/2108.05301.pdf) |[code](https://github.com/JingyunLiang/HCFlow) | SR/Rescale, learns a bijective mapping |
+|Deep Reparametrization of Multi-Frame Super-Resolution and Denoising | - | [iccv21](https://arxiv.org/pdf/2108.08286.pdf) |- | Multi-Frame，deep reparametrization of the classical MAP objective |
+|Attention-based Multi-Reference Learning for Image Super-Resolution | AMRSR | [iccv21](https://arxiv.org/pdf/2108.13697.pdf) |[code](https://marcopesavento.github.io/AMRSR) | RefSR， without frame alignment， Hierarchical Attention-based Similarity |
+| COMISR: Compression-Informed Video Super-Resolution          | COMISR                  | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_COMISR_Compression-Informed_Video_Super-Resolution_ICCV_2021_paper.pdf) | [code](https://github.com/google-research/google-research/tree/master/comisr) | ***VSR***, bi-directional recurrent, warping, detail-preserving flow estimation,  Laplacian enhancement |
+|Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhan_Achieving_On-Mobile_Real-Time_Super-Resolution_With_Neural_Architecture_and_Pruning_Search_ICCV_2021_paper.pdf) |- | SISR, real-time sr, NAS |
+|Event Stream Super-Resolution via Spatiotemporal Constraint Learning | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_Event_Stream_Super-Resolution_via_Spatiotemporal_Constraint_Learning_ICCV_2021_paper.pdf) |- | event stream SR |
+|Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution | DFSA | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Magid_Dynamic_High-Pass_Filtering_and_Multi-Spectral_Attention_for_Image_Super-Resolution_ICCV_2021_paper.pdf) |- | SISR, SOTA, matrix multi-spectral channel attention |
+|Context Reasoning Attention Network for Image Super-Resolution | CRAN | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhang_Context_Reasoning_Attention_Network_for_Image_Super-Resolution_ICCV_2021_paper.pdf) |- | SISR, SOTA, context reasoning attention |
+|EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Han_EvIntSR-Net_Event_Guided_Multiple_Latent_Frames_Reconstruction_and_Super-Resolution_ICCV_2021_paper.pdf) |- | EvIntSR |
+|Deep Blind Video Super-Resolution | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Pan_Deep_Blind_Video_Super-Resolution_ICCV_2021_paper.pdf) |- | ***Blind VSR*** |
+|Super Resolve Dynamic Scene From Continuous Spike Streams | MGSR | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhao_Super_Resolve_Dynamic_Scene_From_Continuous_Spike_Streams_ICCV_2021_paper.pdf) |- | Spike camera SR |
+|Benchmarking Ultra-High-Definition Image Super-Resolution | MANet | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhang_Benchmarking_Ultra-High-Definition_Image_Super-Resolution_ICCV_2021_paper.pdf) |- | UHD SR dataset, 4K, 8K, SISR |
+|Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Lecouat_Lucas-Kanade_Reloaded_End-to-End_Super-Resolution_From_Raw_Image_Bursts_ICCV_2021_paper.pdf) |[code](https://github.com/bruno-31/lkburst) | Raw Image Bursts SR |
+|Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_Unsupervised_Real-World_Super-Resolution_A_Domain_Adaptation_Perspective_ICCV_2021_paper.pdf) |- | unpaired realSR, domain adaptation |
+|Real-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme | - | [iccv21](https://openaccess.thecvf.com/content/ICCV2021/papers/Yang_Real-World_Video_Super-Resolution_A_Benchmark_Dataset_and_a_Decomposition_Based_ICCV_2021_paper.pdf) |[code](https://github.com/IanYeung/RealVSR) | ***RealVSR*** dataset |