Skip to content

Files

1434 lines (834 loc) · 42.3 KB

README.md

File metadata and controls

1434 lines (834 loc) · 42.3 KB

ECCV2020-Code

ECCV 2020 论文开源项目合集,同时欢迎各位大佬提交issue,分享ECCV 2020开源项目

关于往年CV顶会论文(如CVPR 2020、ICCV 2019、ECCV 2018)以及其他优质CV论文和大盘点,详见: https://github.com/amusi/daily-paper-computer-vision

CNN

Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid

WeightNet: Revisiting the Design Space of Weight Networks

Feature Pyramid Transformer

Dynamic Group Convolution for Accelerating Convolutional Neural Networks

Learning to Learn Parameterized Classification Networks for Scalable Input Images

Rethinking Bottleneck Structure for Efficient Mobile Network Design

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

图像分类

Learning to Learn Parameterized Classification Networks for Scalable Input Images

Learning To Classify Images Without Labels

2D目标检测

Learning Data Augmentation Strategies for Object Detection

AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling

Side-Aware Boundary Localization for More Precise Object Detection

TIDE: A General Toolbox for Identifying Object Detection Errors

Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

Dense RepPoints: Representing Visual Objects with Dense Point Sets

Corner Proposal Network for Anchor-free, Two-stage Object Detection

BorderDet: Border Feature for Dense Object Detection

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

Probabilistic Anchor Assignment with IoU Prediction for Object Detection

HoughNet: Integrating near and long-range evidence for bottom-up object detection

OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features

End-to-End Object Detection with Transformers

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features

Object Detection with a Unified Label Space from Multiple Datasets

弱监督目标检测

Enabling Deep Residual Networks for Weakly Supervised Object Detection

UFO²: A Unified Framework towards Omni-supervised Object Detection

Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer

域自适应目标检测

Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection

Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector

Few-Shot 目标检测

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

水下目标检测

Dual Refinement Underwater Object Detection Network

遥感旋转目标检测

PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

Arbitrary-Oriented Object Detection with Circular Smooth Label

3D目标检测

Rethinking Pseudo-LiDAR Representation

Pillar-based Object Detection for Autonomous Driving

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection

视频目标检测

Mining Inter-Video Proposal Relations for Video Object Detection

Learning Where to Focus for Efficient Video Object Detection

语义分割

SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection

Tensor Low-Rank Reconstruction for Semantic Segmentation

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild

SegFix: Model-Agnostic Boundary Refinement for Segmentation

Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

实例分割

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation

Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation

Boundary-preserving Mask R-CNN

Conditional Convolutions for Instance Segmentation

SOLO: Segmenting Objects by Locations

全景分割

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

视频目标分割

Collaborative Video Object Segmentation by Foreground-Background Integration

Video Object Segmentation with Episodic Graph Memory Networks

单/多目标跟踪

Ocean: Object-aware Anchor-Free Tracking

多目标跟踪

Towards Real-Time Multi-Object Tracking

Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking

Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking

Ocean: Object-aware Anchor-Free Tracking

TAO: A Large-Scale Benchmark for Tracking Any Object

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

GAN

Rewriting a Deep Generative Model

Contrastive Learning for Unpaired Image-to-Image Translation

XingGAN for Person Image Generation

NAS

Are Labels Necessary for Neural Architecture Search?

Rethinking Bottleneck Structure for Efficient Mobile Network Design

Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search

3D点云(分类/分割/配准/补全等)

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds

A Closer Look at Local Aggregation Operators in Point Cloud Analysis

3D点云补全

Multimodal Shape Completion via Conditional Generative Adversarial Networks

GRNet: Gridding Residual Network for Dense Point Cloud Completion

3D点云生成

Progressive Point Cloud Deconvolution Generation Network

人脸(检测/识别/解析等)

人脸检测

ProgressFace: Scale-Aware Progressive Learning for Face Detection

人脸识别

Explainable Face Recognition

3D人脸重建

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

人脸活体检测

CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations

人脸解析

Edge-aware Graph Representation Learning and Reasoning for Face Parsing

DeepFakes

What makes fake images detectable? Understanding properties that generalize

其他

Lifespan Age Transformation Synthesis

Re-ID

行人重识别

Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization

Appearance-Preserving 3D Convolution for Video-based Person Re-identification

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

Faster Person Re-Identification

Temporal Complementary Learning for Video Person Re-Identification

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

Robust Re-Identification by Multiple Views Knowledge Distillation

Multiple Expert Brainstorming for Domain Adaptive Person Re-identification

车辆重识别

Simulating Content Consistent Vehicle Datasets with Attribute Descent

Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network

显著性检测(SOD)

Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

Suppress and Balance: A Simple Gated Network for Salient Object Detection

Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection

A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection

Cross-Modal Weighting Network for RGB-D Salient Object Detection

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

Highly Efficient Salient Object Detection with 100K Parameters

模型压缩(剪枝/知识蒸馏等)

EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

视频理解/行为识别/行为检测

AssembleNet++: Assembling Modality Representations via Attention Connections

LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

Context-Aware RCNN: A Baseline for Action Detection in Videos

Actions as Moving Points

SF-Net: Single-Frame Supervision for Temporal Action Localization

Asynchronous Interaction Aggregation for Action Detection

场景文本检测

Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting

场景文本识别

Adaptive Text Recognition through Visual Matching

Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting

特征点检测/描述符/匹配

Learning and aggregating deep local descriptors for instance-level recognition

Online Invariance Selection for Local Feature Descriptors

Single-Image Depth Prediction Makes Feature Matching Easier

姿态估计

Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose

Key Frame Proposal Network for Efficient Pose Estimation in Videos

3D人体姿态估计

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

6D位姿估计

CosyPose: Consistent multi-view multi-object 6D pose estimation

深度估计

Learning Stereo from Single Images

单目深度估计

P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

深度补全

Non-Local Spatial Propagation Network for Depth Completion

域泛化

Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

超分辨率

图像超分辨率

Learning the Super-Resolution Space with Normalizing Flow

Deep Decomposition Learning for Inverse Imaging Problems

Component Divide-and-Conquer for Real-World Image Super-Resolution

Learning with Privileged Information for Efficient Image Super-Resolution

Spatial-Angular Interaction for Light Field Image Super-Resolution

Invertible Image Rescaling

视频超分辨率

Video Super-Resolution with Recurrent Structure-Detail Network

去模糊

图像去模糊

End-to-end Interpretable Learning of Non-blind Image Deblurring

视频去模糊

Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring

去雨

Rethinking Image Deraining via Rain Streaks and Vapors

图像/视频恢复

Learning Enriched Features for Real Image Restoration and Enhancement

图像/视频修复(补全)

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

Learning Joint Spatial-Temporal Transformations for Video Inpainting

Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations

风格迁移

Domain-Specific Mappings for Generative Adversarial Style Transfer

三维重建

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

图像描述

Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards

图像检索

SOLAR: Second-Order Loss and Attention for Image Retrieval

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

光流估计

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

视频插帧

BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation

车道线检测

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

Ultra Fast Structure-aware Deep Lane Detection

Gen-LaneNet: a generalized and scalable approach for 3D lane detection

轨迹预测

SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras

线段检测

Deep Hough-Transform Line Priors

视线估计

ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation

眼动追踪

Towards End-to-end Video-based Eye-Tracking

对抗攻击

Adversarial Ranking Attack and Defense

Square Attack: a query-efficient black-box adversarial attack via random search

数据集

Long-term Human Motion Prediction with Scene Context

Object Detection with a Unified Label Space from Multiple Datasets

Simulating Content Consistent Vehicle Datasets with Attribute Descent

InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image

SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

Detecting natural disasters, damage, and incidents in the wild

Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking

3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View

Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards

From Shadow Segmentation to Shadow Removal

LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities

Component Divide-and-Conquer for Real-World Image Super-Resolution

Towards End-to-end Video-based Eye-Tracking

Reconstructing NBA Players

CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations

PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

DanbooRegion: An Illustration Region Dataset

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

Gen-LaneNet: a generalized and scalable approach for 3D lane detection

TAO: A Large-Scale Benchmark for Tracking Any Object

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

AiR: Attention with Reasoning Capability

其他

Defocus Blur Detection via Depth Distillation

Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition

Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems

From Shadow Segmentation to Shadow Removal

论文:http://xxx.itp.ac.cn/abs/2008.00267

代码和数据集:https://www3.cs.stonybrook.edu/~cvl/projects/FSS2SR/index.html

Funnel Activation for Visual Recognition

Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions

Consensus-Aware Visual-Semantic Embedding for Image-Text Matching

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

AiR: Attention with Reasoning Capability

Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

A Generic Visualization Approach for Convolutional Neural Networks

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches

GIQA: Generated Image Quality Assessment

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

AiR: Attention with Reasoning Capability

不确定中没中

Relation Aware Panoptic Segmentation

Spatial-Angular Interaction for Light Field Image Super-Resolution

TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

Self-supervising Fine-grained Region Similarities for IBL

https://github.com/lelechen63/eccv2020