目录
- CVPR 2022
-
- 图像超分
- 盲超分
- 视频超分
- 特殊场景
- AAAI 2022
-
- 图像超分
- 特殊场景
- WACV 2022
-
- 图像超分
- 视频超分
- 特殊场景
- 参考资料
CVPR 2022
官网链接:http://CVPR2022.thecvf.com 会议时间:2021年6月19日至6月24日
现在,超分辨率方向上收到的论文总结如下纠正遗漏。
图像超分
- Local Texture Estimator for Implicit Representation Function
- Paper: https://ipl.dgist.ac.kr/LTE_cvpr.pdf
- Code: https://github.com/jaewon-lee-b/lte
- Reflash Dropout in Image Super-Resolution
- Paper: https://arxiv.org/abs/2112.12089
- Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
- Paper: https://arxiv.org/abs/2203.00911
盲超分
- Deep Constrained Least Squares for Blind Image Super-Resolution
- Paper: https://arxiv.org/abs/2202.07508
- Code: https://github.com/megvii-research/DCLS-SR
- Learning the Degradation Distribution for Blind Image Super-Resolution
- Paper: https://arxiv.org/abs/2203.04962
- Code: https://github.com/greatlog/UnpairedSR
- Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
- Paper: https://arxiv.org/abs/2107.00986
- Code: https://github.com/zsyOAOA/BSRDM
视频超分
-
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
- Paper: https://arxiv.org/abs/2204.07114
-
RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution
- Paper: https://arxiv.org/abs/2203.14186
- Code: https://github.com/llmpass/RSTT
- Keywords: Transformer
-
Reference-based Video Super-Resolution Using Multi-Camera Video Triplets
- Paper: https://arxiv.org/abs/2203.14537
- Code: https://github.com/codeslake/RefVSR
-
Learning Trajectory-Aware Transformer for Video Super-Resolution
- Paper: https://arxiv.org/abs/2204.04216
- Code: https://github.com/researchmm/TTVSR
特殊场景
- A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution
- Paper: https://arxiv.org/abs/2203.09388
- Code: https://github.com/mjq11302010044/TATT
- Keywords: Scene Text
- Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
- Paper: https://arxiv.org/abs/2203.09195
- Code: https://github.com/csjliang/LDL
- Keywords: Realistic
AAAI 2022
AAAI它是中国计算机学会历史最悠久、内容最广泛的国际顶级学术会议之一(CCF)A级国际学术会议推荐人工智能领域之一。据了解,本次会议收到全球9215篇论文,接受率仅为15%,创历史新低。
官方网址:https://aaai.org/Conferences/AAAI-22/
图像超分
- Efficient Non-Local Contrastive Attention for Image Super-Resolution
- Paper: https://arxiv.org/abs/2201.03794
- Code: https://github.com/Zj-BinXia/ENLCA
- Keywords: Attention
- Best-Buddy GANs for Highly Detailed Image Super-Resolution
- Paper: https://arxiv.org/abs/2103.15295
- Code: https://github.com/Jia-Research-Lab/Simple-SR
- Keywords: GAN
特殊场景
-
Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
- Paper: https://arxiv.org/abs/2112.08171
- Code: https://github.com/FudanVI/FudanOCR/tree/main/text-gestalt
- Keywords: Scene Text
-
Detail-Preserving Transformer for Light Field Image Super-Resolution
- Paper: https://arxiv.org/abs/2201.00346
- Code: https://github.com/BITszwang/DPT Keywords: Light Field
-
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-Resolution
- Paper: https://arxiv.org/abs/2201.04358
- Code: https://github.com/Zj-BinXia/AMSA
- Keywords: Reference-Based
-
Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution
- Paper: https://arxiv.org/abs/2112.08655
- Code: https://github.com/IVIPLab/FDIWN
- Keywords: Lightweight
-
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution
- Paper: https://arxiv.org/abs/2201.04364
- Keywords: Multi-task
WACV 2022
WACV是IEEE Winter Conference on Applications of Computer Vision缩写,根据谷歌学术显示在 Computer Vision & Pattern Recognition 领域, WACV是排在CVPR \ ICCV \ ECCV \ BMVC 之后的较高质量的国际会议。
官方网址:https://openaccess.thecvf.com/WACV2022
图像超分
- DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks
- Paper: https://arxiv.org/abs/2012.11230
- edge-SR: Super-Resolution For The Masses
- Paper: https://arxiv.org/abs/2108.10335
- Code: https://github.com/pnavarre/eSR
视频超分
- MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution
- Paper: https://arxiv.org/abs/2110.15327
- Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution
- Paper: https://arxiv.org/abs/2111.03649
- Code: http://git.io/AdFlow
- Keywords: Photo-Realistic, Flow
特殊场景
- Hyperspectral Image Super-Resolution With RGB Image Super-Resolution as an Auxiliary Task
- Paper: https://arxiv.org/abs/2101.07589
- Code: https://github.com/kli8996/HSISR.git
- MoESR: Blind Super-Resolution Using Kernel-Aware Mixture of Experts
- Paper: Open Access
- Code: https://github.com/memad73/MoESR
- Keywords: Blind
- Multi-Dimensional Dynamic Model Compression for Efficient Image Super-Resolution
- Paper: Open Access
- Keywords: Model Compression
参考资料
- CVPR 2022 全面盘点:最新350篇论文分方向汇总 / 代码 / 解读 / 直播 / 项目(更新中)
- Awesome-Super-Resolution
- CVPR2022-Paper-Code-Interpretation