ECCV的全称是European Conference on Computer Vision(欧洲计算机视觉国际会议) ，两年一次，是计算机视觉三大会议（另外两个是ICCV和CVPR）之一。每次会议在全球范围录用论文300篇左右，主要的录用论文都来自美国、欧洲等顶尖实验室及研究所，中国大陆的论文数量一般在10-20篇之间。
本文整理了2020年ECCV所有Accept的论文，论文完整版源地址：https://eccv2020.eu/accepted-papers/
精选论文列表
Quaternion Equivariant Capsule Networks for 3D Point Clouds
DeepFit: 3D Surface Fitting by Neural Network Weighted Least Squares
MoSaNAS: Multi-Objective Surrogate-Assisted Neural Architecture Search
Describing Textures using Natural Language
Empowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity Recognition
AiR: Attention with Reasoning Capability
Self6D: Self-Supervised Monocular 6D Object Pose Estimation
Invertible Image Rescaling
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation
Crowdsampling the Plenoptic Function
End-to-End Estimation of Multi-Person 3D Poses from Multiple Cameras
End-to-End Object Detection with Transformers
DeepSFM: Structure From Motion Via Deep Bundle Adjustment
Ladybird: Deep Implicit Field Based 3D Reconstruction with Sampling and Symmetry
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Conditional Convolutions for Instance Segmentation
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
Privacy Preserving Structure-from-Motion
Rewriting a Deep Generative Model
Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets
Long-term Human Motion Prediction with Scene Context
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes
MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images
Learning and aggregating deep local descriptors for instance-level recognition
A Consistently Fast and Globally Optimal Solution to the Perspective-n-Point Problem
Learn to Recover Visible Color for Video Surveillance in a Day
Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single-view Images
Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation
BorderDet: Border Feature for Dense Object Detection
Regularization with Latent Space Virtual Adversarial Training
Du$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels
Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning
Targeted Attack for Deep Hashing based Retrieval
Gradient Centralization: A New Optimization Technique for Deep Neural Networks
Content-Aware Unsupervised Deep Homography Estimation
Multi-View Optimization of Local Feature Geometry
Efï¬cient Model Fitting by Combining Lifted Optimization with Phong Surface Models
Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video
Learning Stereo from Single Images
Prototype Rectification for Few-Shot Learning
Learning Feature Descriptors using Camera Pose Supervision
Semantic Flow for Fast and Accurate Scene Parsing
Appearance Consensus Driven Self-Supervised Human Mesh Recovery
Diffraction Line Imaging
Aligning and Projecting Images to Class-conditional Generative Networks
Suppress and Balance: A Simple Gated Network for Salient Object Detection
Visual Memorability for Robotic Interestingness Prediction via Unsupervised Online Learning
Post-Training Piecewise Linear Quantization for Deep Neural Networks
Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
In-Home Daily-Life Captioning Using Radio Signals
Self-Challenging Improves Cross-Domain Generalization
A Competence-aware Curriculum for Visual Concepts Learning via Question Answering
Multi-task Learning Increases Adversarial Robustness
S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
Improving Deep Video Compression by Resolution-adaptive Flow Coding
Motion Capture from Internet Videos
Appearance-Preserving 3D Convolution for Video-based Person Re-identification
Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Coherent full scene 3D reconstruction from a single RGB image
Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
Domain-invariant Stereo Matching Networks
DeepHandMesh: Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling from a Single RGB Image
Content Adaptive and Error Propagation Aware Deep Video Compression
Towards Streaming Image Understanding
Towards Automated Testing and Robustification by Semantic Adversarial Data Generation
Adversarial Generative Grammars for Human Activity Prediction
Greedy Sampler and Dumb Learner: A Surprisingly Effective Approach for Continual Learning
Learning Lane Graph Representations for Motion Forecasting
What Matters in Unsupervised Optical Flow
Synthesis and Completion of Facades from Satellite Imagery
Mapillary Planet-Scale Depth Dataset
V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
Cross-Domain Cascaded Deep Translation
"Look Ma, no landmarks!" - Unsupervised, model-based dense face alignment
Online Invariance Selection for Local Feature Descriptors
Rethinking image inpainting via a mutual encoder-decoder with feature equalization
TextCaps: a Dataset for Image Captioning with Reading Comprehension
It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
Learning What to Learn for Video Object Segmentation
SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing
LIMP: Learning Latent Shape Representations with Metric Preservation Priors
Unsupervised Sketch-to-Photo Synthesis
A simple way to make neural networks robust against diverse image corruptions
SoftpoolNet: Shape Descriptor for Point Cloud Completion and Classification
Hierarchical Face Aging through Disentangled Latent Characteristics
Hybrid Models for Open Set Recognition
TopoGAN: A Topology-Aware Generative Adversarial Network
Learning to Localize Actions from Moments
ForkGAN: Seeing into the Rainy Night
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval
A Simple and Versatile Framework for Image-to-Image Translation
ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices
Fair Attribute Classification through Latent Space De-biasing
HMOR: Hierarchical Multi-person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation
Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
A Unified Framework of Surrogate Loss by Refactorization and Interpolation
Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images
Memory-augmented Dense Predictive Coding for Video Representation Learning
PointMixup: Augmentation for Point Clouds
Identity-Guided Human Semantic Parsing Learning for Person Re-Identification
Learning Gradient Fields for Shape Generation
Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
Corner Proposal Network for Anchor-free, Two-stage Object Detection
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click
Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing
Learning Delicate Local Representations for Multi-Person Pose Estimation
Learning to plan with uncertain topological maps
Neural Design Network: Graphic Layout Generation with Constraints
Learning Open Set Network with Discriminative Reciprocal Points
Convolutional Occupancy Networks
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
A General Toolbox for Understanding Errors in Object Detection
PointContrast: Unsupervised Pretraining for 3D Point Cloud Understanding
DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation
Circumventing Outliers of AutoAugment with Knowledge Distillation
S2DNet: Learning accurate correspondences for sparse-to-dense feature matching
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
Video Object Segmentation with Graph Memory Network
Rethinking Bottleneck Structure for Efficient Mobile Network Design
Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks
Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach
A Tool for Measuring and Mitigating Bias in Visual Datasets
Contrastive Learning for Weakly Supervised Phrase Grounding
Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis
Studying the Transferability of Adversarial Attacks on Object Detectors
TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images
Semi-Siamese Training for Shallow Face Learning
GAN Slimming: All-in-One Unified GAN Compression
Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition
Binarized Neural Network for Single Image Super Resolution
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
Adaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
Hamiltonian Dynamics for Real-World Shape Interpolation
Learning to Scale Multilingual Representations for Vision-Language Tasks