CVPR 2021 论文和开源项目合集(Papers with Code)

【CVPR 2021 论文开源目录】

https://github.com/amusi/CVPR2021-Papers-with-Code

• Backbone

• NAS

• GAN

• Visual Transformer

• 自监督(Self-Supervised)

• 目标检测(Object Detection)

• 实例分割(Instance Segmentation)

• 全景分割(Panoptic Segmentation)

• 视频理解/行为识别(Video Understanding)

• 人脸识别(Face Recognition)

• 人脸活体检测(Face Anti-Spoofing)

• Deepfake检测(Deepfake Detection)

• 人脸年龄估计(Age-Estimation)

• 人脸解析(Human Parsing)

• 超分辨率(Super-Resolution)

• 图像恢复(Image Restoration)

• 3D目标检测(3D Object Detection)

• 3D语义分割(3D Semantic Segmentation)

• 3D目标跟踪(3D Object Tracking)

• 3D点云配准(3D Point Cloud Registration)

• 6D位姿估计(6D Pose Estimation)

• 深度估计(Depth Estimation)

• 对抗样本(Adversarial-Examples)

• 图像检索(Image Retrieval)

• Zero-Shot Learning

• 视觉推理(Visual Reasoning)

• "人-物"交互(HOI)检测

• 阴影去除(Shadow Removal)

• 数据集(Datasets)

• 其他(Others)

• 不确定中没中(Not Sure)

Backbone

Coordinate Attention for Efficient Mobile Network Design

• Paper: https://arxiv.org/abs/2103.02907

• Code: https://github.com/Andrew-Qibin/CoordAttention

Inception Convolution with Efficient Dilation Search

• Paper: https://arxiv.org/abs/2012.13587

• Code: None

RepVGG: Making VGG-style ConvNets Great Again

• Paper: https://arxiv.org/abs/2101.03697

• Code: https://github.com/DingXiaoH/RepVGG

NAS

Inception Convolution with Efficient Dilation Search

• Paper: https://arxiv.org/abs/2012.13587

• Code: None

GAN

Training Generative Adversarial Networks in One Stage

• Paper: https://arxiv.org/abs/2103.00430

• Code: None

Closed-Form Factorization of Latent Semantics in GANs

• Homepage: https://genforce.github.io/sefa/

• Paper: https://arxiv.org/abs/2007.06600

• Code: https://github.com/genforce/sefa

Anycost GANs for Interactive Image Synthesis and Editing

• Paper: https://arxiv.org/abs/2103.03243

• Code: https://github.com/mit-han-lab/anycost-gan

Image-to-image Translation via Hierarchical Style Disentanglement

• Paper: https://arxiv.org/abs/2103.01456

• Code: https://github.com/imlixinyang/HiSD

Visual Transformer

End-to-End Video Instance Segmentation with Transformers

• Paper(Oral): https://arxiv.org/abs/2011.14503

• Code: None

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

• Paper(Oral): https://arxiv.org/abs/2011.09094

• Code: https://github.com/dddzg/up-detr

End-to-End Human Object Interaction Detection with HOI Transformer

• Paper: https://arxiv.org/abs/2103.04503

• Code: https://github.com/bbepoch/HoiTransformer

Transformer Interpretability Beyond Attention Visualization

• Paper: https://arxiv.org/abs/2012.09838

• Code: https://github.com/hila-chefer/Transformer-Explainability

自监督

Dense Contrastive Learning for Self-Supervised Visual Pre-Training

• Paper: https://arxiv.org/abs/2011.09157

• Code: https://github.com/WXinlong/DenseCL

目标检测(Object Detection)

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

• Paper(Oral): https://arxiv.org/abs/2011.09094

• Code: https://github.com/dddzg/up-detr

General Instance Distillation for Object Detection

• Paper: https://arxiv.org/abs/2103.02340

• Code: None

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

• Paper: https://arxiv.org/abs/2103.01903

• Code: None

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge

• Homepage: http://rl.uni-freiburg.de/research/multimodal-distill

• Paper: https://arxiv.org/abs/2103.01353

• Code: http://rl.uni-freiburg.de/research/multimodal-distill

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection

• Paper: https://arxiv.org/abs/2011.12885

• Code: https://github.com/implus/GFocalV2

Multiple Instance Active Learning for Object Detection

• Paper: https://github.com/yuantn/MIAL/raw/master/paper.pdf

• Code: https://github.com/yuantn/MIAL

Towards Open World Object Detection

• Paper: https://arxiv.org/abs/2103.02603

• Code: https://github.com/JosephKJ/OWOD

实例分割(Instance Segmentation)

End-to-End Video Instance Segmentation with Transformers

• Paper(Oral): https://arxiv.org/abs/2011.14503

• Code: None

Zero-shot instance segmentation（Not Sure）

• Paper: None

• Code: https://github.com/CVPR2021-pape-id-1395/CVPR2021-paper-id-1395

全景分割(Panoptic Segmentation)

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

• Paper: https://arxiv.org/abs/2103.02584

• Code: None

视频理解/行为识别(Video Understanding)

TDN: Temporal Difference Networks for Efficient Action Recognition

• Paper: https://arxiv.org/abs/2012.10071

• Code: https://github.com/MCG-NJU/TDN

人脸识别(Face Recognition)

WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition

• Homepage: https://www.face-benchmark.org/

• Paper: https://arxiv.org/abs/2103.04098

• Dataset: https://www.face-benchmark.org/

When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework

• Paper(Oral): https://arxiv.org/abs/2103.01520

• Code: https://github.com/Hzzone/MTLFace

• Dataset: https://github.com/Hzzone/MTLFace

人脸活体检测(Face Anti-Spoofing)

Cross Modal Focal Loss for RGBD Face Anti-Spoofing

• Paper: https://arxiv.org/abs/2103.00948

• Code: None

Deepfake检测(Deepfake Detection)

Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain

• Paper：https://arxiv.org/abs/2103.01856

• Code: None

Multi-attentional Deepfake Detection

• Paper：https://arxiv.org/abs/2103.02406

• Code: None

人脸年龄估计(Age Estimation)

PML: Progressive Margin Loss for Long-tailed Age Classification

• Paper: https://arxiv.org/abs/2103.02140

• Code: None

人体解析(Human Parsing)

Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing

• Paper: https://arxiv.org/abs/2103.04570

• Code: https://github.com/tfzhou/MG-HumanParsing

超分辨率(Super-Resolution)

ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

• Paper: https://arxiv.org/abs/2103.04039

• Code: https://github.com/Xiangtaokong/ClassSR

AdderSR: Towards Energy Efficient Image Super-Resolution

• Paper: https://arxiv.org/abs/2009.08891

• Code: None

图像恢复(Image Restoration)

Multi-Stage Progressive Image Restoration

• Paper: https://arxiv.org/abs/2102.02808

• Code: https://github.com/swz30/MPRNet

3D目标检测(3D Object Detection)

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

• Paper: None

• Code: https://github.com/Vegeta2020/SE-SSD

Center-based 3D Object Detection and Tracking

• Paper: https://arxiv.org/abs/2006.11275

• Code: https://github.com/tianweiy/CenterPoint

Categorical Depth Distribution Network for Monocular 3D Object Detection

• Paper: https://arxiv.org/abs/2103.01100

• Code: None

3D语义分割(3D Semantic Segmentation)

Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges

• Homepage: https://github.com/QingyongHu/SensatUrban

• Paper: http://arxiv.org/abs/2009.03137

• Code: https://github.com/QingyongHu/SensatUrban

• Dataset: https://github.com/QingyongHu/SensatUrban

3D目标跟踪(3D Object Trancking)

Center-based 3D Object Detection and Tracking

• Paper: https://arxiv.org/abs/2006.11275

• Code: https://github.com/tianweiy/CenterPoint

3D点云配准(3D Point Cloud Registration)

PREDATOR: Registration of 3D Point Clouds with Low Overlap

• Paper: https://arxiv.org/abs/2011.13005

• Code: https://github.com/ShengyuH/OverlapPredator

6D位姿估计(6D Pose Estimation)

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

• Paper: https://arxiv.org/abs/2103.02242

• Code: https://github.com/ethnhe/FFB6D

深度估计

Depth from Camera Motion and Object Detection

• Paper: https://arxiv.org/abs/2103.01468

• Code: https://github.com/griffbr/ODMD

• Dataset: https://github.com/griffbr/ODMD

对抗样本

Natural Adversarial Examples

• Paper: https://arxiv.org/abs/1907.07174

• Code: https://github.com/hendrycks/natural-adv-examples

图像检索(Image Retrieval)

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

• Paper: https://arxiv.org/abs/2103.02927

• Code: None

Zero-Shot Learning

Counterfactual Zero-Shot and Open-Set Visual Recognition

• Paper: https://arxiv.org/abs/2103.00887

• Code: https://github.com/yue-zhongqi/gcm-cf

视觉推理(Visual Reasoning)

Transformation Driven Visual Reasoning

• homepage: https://hongxin2019.github.io/TVR/

• Paper: https://arxiv.org/abs/2011.13160

• Code: https://github.com/hughplay/TVR

"人-物"交互(HOI)检测

End-to-End Human Object Interaction Detection with HOI Transformer

• Paper: https://arxiv.org/abs/2103.04503

• Code: https://github.com/bbepoch/HoiTransformer

阴影去除(Shadow Removal)

Auto-Exposure Fusion for Single-Image Shadow Removal

• Paper: https://arxiv.org/abs/2103.01255

• Code: https://github.com/tsingqguo/exposure-fusion-shadow-removal

数据集(Datasets)

Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food

• Paper: https://arxiv.org/abs/2103.03375

• Dataset: None

Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges

• Homepage: https://github.com/QingyongHu/SensatUrban

• Paper: http://arxiv.org/abs/2009.03137

• Code: https://github.com/QingyongHu/SensatUrban

• Dataset: https://github.com/QingyongHu/SensatUrban

When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework

• Paper(Oral): https://arxiv.org/abs/2103.01520

• Code: https://github.com/Hzzone/MTLFace

• Dataset: https://github.com/Hzzone/MTLFace

Depth from Camera Motion and Object Detection

• Paper: https://arxiv.org/abs/2103.01468

• Code: https://github.com/griffbr/ODMD

• Dataset: https://github.com/griffbr/ODMD

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge

• Homepage: http://rl.uni-freiburg.de/research/multimodal-distill

• Paper: https://arxiv.org/abs/2103.01353

• Code: http://rl.uni-freiburg.de/research/multimodal-distill

Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

• Paper: https://arxiv.org/abs/2012.02206

• Code: https://github.com/daveredrum/Scan2Cap

• Dataset: https://github.com/daveredrum/ScanRefer

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge

• Paper: https://arxiv.org/abs/2103.01353

• Code: http://rl.uni-freiburg.de/research/multimodal-distill

• Dataset: http://rl.uni-freiburg.de/research/multimodal-distill

其他(Others)

Knowledge Evolution in Neural Networks

• Paper(Oral): https://arxiv.org/abs/2103.05152

• Code: https://github.com/ahmdtaha/knowledge_evolution

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning

• Paper: https://arxiv.org/abs/2103.02148

• Code: https://github.com/guopengf/FLMRCM

SGP: Self-supervised Geometric Perception

• Oral

• Paper: https://arxiv.org/abs/2103.03114

• Code: https://github.com/theNded/SGP

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning

• Paper: https://arxiv.org/abs/2103.02148

• Code: https://github.com/guopengf/FLMRCM

Diffusion Probabilistic Models for 3D Point Cloud Generation

• Paper: https://arxiv.org/abs/2103.01458

• Code: https://github.com/luost26/diffusion-point-cloud

Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

• Paper: https://arxiv.org/abs/2012.02206

• Code: https://github.com/daveredrum/Scan2Cap

• Dataset: https://github.com/daveredrum/ScanRefer

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge

• Paper: https://arxiv.org/abs/2103.01353

• Code: http://rl.uni-freiburg.de/research/multimodal-distill

• Dataset: http://rl.uni-freiburg.de/research/multimodal-distill

不确定中没中(Not Sure)

CT Film Recovery via Disentangling Geometric Deformation and Photometric Degradation: Simulated Datasets and Deep Models

• Paper: none

• Code: https://github.com/transcendentsky/Film-Recovery

Toward Explainable Reflection Removal with Distilling and Model Uncertainty

• Paper: none

• Code: https://github.com/ytpeng-aimlab/CVPR-2021-Toward-Explainable-Reflection-Removal-with-Distilling-and-Model-Uncertainty

DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation

• Paper: none

• Code: https://github.com/lhaippp/DeepOIS

Exploring Adversarial Fake Images on Face Manifold

• Paper: none

• Code: https://github.com/ldz666666/Style-atk

Uncertainty-Aware Semi-Supervised Crowd Counting via Consistency-Regularized Surrogate Task

• Paper: none

• Code: https://github.com/yandamengdanai/Uncertainty-Aware-Semi-Supervised-Crowd-Counting-via-Consistency-Regularized-Surrogate-Task

Temporal Contrastive Graph for Self-supervised Video Representation Learning

• Paper: none

• Code: https://github.com/YangLiu9208/TCG

Boosting Monocular Depth Estimation Models to High-Resolution via Context-Aware Patching

• Paper: none

• Code: https://github.com/ouranonymouscvpr/cvpr2021_ouranonymouscvpr

Fast and Memory-Efficient Compact Bilinear Pooling

• Paper: none

• Code: https://github.com/cvpr2021kp2/cvpr2021kp2

Identification of Empty Shelves in Supermarkets using Domain-inspired Features with Structural Support Vector Machine

• Paper: none

• Code: https://github.com/gapDetection/cvpr2021

Estimating A Child's Growth Potential From Cephalometric X-Ray Image via Morphology-Aware Interactive Keypoint Estimation

• Paper: none

• Code: https://github.com/interactivekeypoint2020/Morph

https://github.com/ShaoQiangShen/CVPR2021

https://github.com/gillesflash/CVPR2021

https://github.com/anonymous-submission1991/BaLeNAS

https://github.com/cvpr2021dcb/cvpr2021dcb

https://github.com/anonymousauthorCV/CVPR2021_PaperID_8578

https://github.com/AldrichZeng/FreqPrune

https://github.com/Anonymous-AdvCAM/Anonymous-AdvCAM

https://github.com/ddfss/datadrive-fss