计算机视觉_CVPR2021_论文代码_汇总资源包_1741783772.zip

## CVPR_2021_Papers汇总，主要包括论文链接、代码地址、文章解读等等 ### 关注公众号【深度学习技术前沿】后台回复 **CVPR2021** 获得百度云下载链接 ------ - 官网链接：http://cvpr2021.thecvf.com<br> - 时间：2021年6月19日-6月25日<br> - 论文接收公布时间：2021年2月28日<br> - CVPR2021官方接受论文列表：[http://cvpr2021.thecvf.com/sites/default/files/2021-03/accepted_paper_ids.txt](http://cvpr2021.thecvf.com/sites/default/files/2021-03/accepted_paper_ids.txt) ------ # CVPR2021接受论文/代码分方向整理(持续更新) # 分类目录： ## Low-Level-Vision(主要包括：超分辨率，图像恢复，去雨，去雾，去模糊，去噪，重建等方向) - [1.超分辨率（Super-Resolution）](#1.超分辨率) - [2.图像去雨（Image Deraining）](#2.图像去雨) - [3.图像去雾（Image Dehazing）](#3.图像去雾) - [4.去模糊（Deblurring）](#4.去模糊) - [5.去噪（Denoising）](#5.去噪) - [6.图像恢复（Image Restoration）](#6.图像恢复) - [7.图像增强（Image Enhancement）](#7.图像增强) - [8.图像去摩尔纹（Image Demoireing）](#8.图像去摩尔纹) - [9.图像阴影去除(Image Shadow Removal)](#9.图像阴影去除) - [10.图像翻译（Image Translation）](#10.图像翻译) - [11.插帧（Frame Interpolation）](#11.插帧) - [12.视频压缩（Video Compression）](#12.视频压缩) - [13.图像编辑(Image Edit)](#13.图像编辑) ## High-Level-Vision（主要包括：图像分类，检测，分割，跟踪，GAN等方向） ### [检测](#detection) * [图像目标检测(Image Object Detection)](#IOD)<br> * [视频目标检测(Video Object Detection)](#VOD)<br> * [三维目标检测(3D Object Detection)](#3DOD)<br> * [动作检测(Activity Detection)](#ActivityDetection)<br> * [异常检测(Anomally Detetion)](#AnomallyDetetion)<br> ### [图像分割(Image Segmentation)](#ImageSegmentation) * [全景分割(Panoptic Segmentation)](#PanopticSegmentation)<br> * [语义分割(Semantic Segmentation)](#SemanticSegmentation)<br> * [实例分割(Instance Segmentation)](#InstanceSegmentation)<br> * [超像素(Superpixel)](#Superpixel)<br> * [视频目标分割(Video Object Segmentation)](#VOS)<br> * [抠图(Matting)](#Matting)<br> ### [人脸(Face)](#Face) * [人脸生成/合成/伪造(Face Generation/Face Synthesis/Face Forgery)](#FaceSynthesis) * [人脸反欺骗(Face Anti-Spoofing)](#FaceAnti-Spoofing) ### [目标跟踪(Object Tracking)](#ObjectTracking) ### [重识别(Re-Identification)](#Re-Identification) * [行为识别/行为识别/动作识别/检测/分割(Action/Activity Recognition)](#ActionRecognition) ### [医学影像(Medical Imaging)](#MedicalImaging) ### [GAN/生成式/对抗式(GAN/Generative/Adversarial)](#GAN) ### [估计(Estimation)](#Estimation) * [人体姿态估计(Human Pose Estimation)](#HumanPoseEstimation) * [手势估计(Gesture Estimation)](#GestureEstimation) * [光流/位姿/运动估计(Flow/Pose/Motion Estimation)](#Flow/Pose/MotionEstimation) ### [三维视觉(3D Vision)](#3DVision) * [三维点云(3D Point Cloud)](#3DPC)<br> * [三维重建(3D Reconstruction)](#3DReconstruction)<br> ## 模型架构与数据处理（主要包括：Transformer, NAS，模型压缩，模型评估） ### [神经网络架构(Neural Network Structure)](#NNS) * [图神经网络(GNN)](#GNN)<br> ### [Transformer](#att) ### [神经网络架构搜索(NAS)](#NAS) ### [数据处理(Data Processing)](#DataProcessing) * [数据增广(Data Augmentation)](#DataAugmentation)<br> * [归一化/正则化(Batch Normalization)](#BatchNormalization)<br> * [图像聚类(Image Clustering)](#ImageClustering)<br> ### [模型压缩(Model Compression)](#ModelCompression) * [知识蒸馏(Knowledge Distillation)](KnowledgeDistillation)<br> ### [模型评估(Model Evaluation)](#ModelEvaluation) ### [数据集(Database)](#Database) <br> ## 其它方向 ### [主动学习(Active Learning)](#ActiveLearning) ### [小样本学习/零样本(Few-shot Learning)](#Few-shotLearning) ### [持续学习(Continual Learning/Life-long Learning)](#ContinualLearning) ### [视觉推理(Visual Reasoning)](#VisualReasoning) ### [迁移学习/domain/自适应](#domain) ### [对比学习(Contrastive Learning)](#ContrastiveLearning) ### [图像/视频检索(Image Retrieval)](#ImageRetrieval) #### [暂无分类](#100) <br> ## CVPR2021的论文解读汇总 - [论文解读](#300) <br><br> <a name="1.超分辨率"></a> ## 1.超分辨率（Super-Resolution） ### Unsupervised Degradation Representation Learning for Blind Super-Resolution - Code：[https://github.com/LongguangWang/DASR](https://github.com/LongguangWang/DASR) ### Data-Free Knowledge Distillation For Image Super-Resolution ### Learning Continuous Image Representation with Local Implicit Image Function(通过局部隐含图像功能学习连续图像表示) - [paepr](https://arxiv.org/abs/2012.09161) - [code](https://github.com/yinboc/liif) - [video](https://youtu.be/6f2roieSY_8) - [project](https://yinboc.github.io/liif/) ### AdderSR: Towards Energy Efficient Image Super-Resolution - Paper：[https://arxiv.org/abs/2009.08891](https://arxiv.org/abs/2009.08891) - [code](https://github.com/huawei-noah/AdderNet) - 解读：[华为开源加法神经网络](https://zhuanlan.zhihu.com/p/113536045) ### Exploring Sparsity in Image Super-Resolution for Efficient Inference - Paper：[https://arxiv.org/abs/2006.09603](https://arxiv.org/abs/2006.09603) - Code：[https://github.com/LongguangWang/SMSR](https://github.com/LongguangWang/SMSR) ### ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic - Code：[https://github.com/Xiangtaokong/ClassSR](https://github.com/Xiangtaokong/ClassSR) ### Cross-MPI: Cross-scale Stereo for Image Super-Resolution using Multiplane Images - Paper：[https://arxiv.org/abs/2011.14631](https://arxiv.org/abs/2011.14631) - Homepage：[http://www.liuyebin.com/crossMPI/crossMPI.html](http://www.liuyebin.com/crossMPI/crossMPI.html) - Analysis：[CVPR 2021，Cross-MPI以底层场景结构为线索的端到端网络，在大分辨率（x8）差距下也可完成高保真的超分辨率](https://zhuanlan.zhihu.com/p/354752197) <a name="2.图像去雨"></a> ## 2.图像去雨（Image Deraining） ### Semi-Supervised Video Deraining with Dynamic Rain Generator(带动态雨水产生器的半监督视频去雨) - [paper](https://arxiv.org/abs/2103.07939) <a name="3.图像去雾"></a> ## 3.图像去雾（Image Dehazing） <a name="4.去模糊"></a> ## 4.去模糊（Deblurring） ### DeFMO: Deblurring and Shape Recovery of Fast Moving Objects(快速移动物体的去模糊和形状恢复) - [paper](https://arxiv.org/abs/2012.00595) - [code](https://github.com/rozumden/DeFMO) - [video](https://www.youtube.com/watch?v=pmAynZvaaQ4) ### ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring(学习用于视频去模糊的全范围体积对应) - [paper](https://arxiv.org/pdf/2103.04260.pdf) <a name="5.去噪"></a> ## 5.去噪（Denoising） <a name="6.图像恢复"></a> ## 6.图像恢复（Image Restoration） ### Multi-Stage Progressive Image Restoration - Paper：[https://arxiv.org/abs/2102.02808](https://arxiv.org/abs/2102.02808) - Code：[https://github.com/swz30/MPRNet](https://github.com/swz30/MPRNet) ### CT Film Recovery via Disentangling Geometric Deformation and Illumination Variation: Simulated Datasets and Deep Models - Paper：[https://arxiv.org/abs/2012.09491](https://arxiv.org/abs/2012.09491) - Code：[https://github.com/transcendentsky/Film-Recovery](https://github.com/transcendentsky/Film-Recovery) ### Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE(使用分层VQ-VAE生成图像修复的多样结构) - [paper](https://arxiv.org/pdf/2103.10022) - [code](https://github.com/USTC-JialunPeng/Diverse-Structure-Inpainting) ### PISE: Person Image Synthesis and Editing with Decoupl