CVPR 2021

2,096 papers

Top Research Directions

Research directions most represented by CVPR 2021 papers.

Generalizing from Synthetic Data to the Real World 40
Resolving Depth Ambiguity in Monocular 3D Reconstruction 22
Accelerating Neural Architecture Search Without Full Model Training 20
Mitigating Error Propagation in Pseudo Labeling 19
Global Context Modeling via Non-Local Spatial Attention 18
Disentangling Attribute Control in Generative Models 17
Loss Weighting via Predictive Uncertainty 17
Why Theoretical FLOPs Fail to Predict Real Latency 17
Generative Hallucination for Disoccluded Region Synthesis 17
Deep Learning on Unstructured 3D Point Clouds 17
Preserving Tiny Features Against Spatial Resolution Degradation 16
Reconstructing Complete Geometry from Partial Point Clouds 16
The Sensitivity of Multi-Objective Loss Balancing 16
Cross Task Generalization in Image Restoration 15
Overcoming the Static Scene Assumption 15

Top Authors

AuthorPapers
Luc Van Gool15
Chunhua Shen13
Dacheng Tao12
Chang Xu11
Chen Change Loy11
Ling Shao11
Yi Yang11
Jiaya Jia10
Marc Pollefeys10
Ziwei Liu10
Alan Yuille9
Hongsheng Li9
Jie Zhou9
Yunhe Wang9
Christian Theobalt8
Hongdong Li8
Houqiang Li8
Huchuan Lu8
Lei Zhang8
Leonidas Guibas8

Impactful Papers

Papers from CVPR 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
SLADE: A Self-Training Framework for Distance Metric Learning
SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation
Slimmable Compressive Autoencoders for Practical Neural Image Compression
Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation
SMD-Nets: Stereo Mixture Density Networks
Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness
SMPLicit: Topology-Aware Generative Model for Clothed People
SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition
Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder
SOLD2: Self-Supervised Occlusion-Aware Line Description and Detection
SOON: Scenario Oriented Object Navigation With Graph-Based Exploration
Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective
Sound-Guided Semantic Image Manipulation
Source-Free Domain Adaptation for Semantic Segmentation
Space-Time Distillation for Video Super-Resolution
Space-Time Neural Irradiance Fields for Free-Viewpoint Video
Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion
Sparse Multi-Path Corrections in Fringe Projection Profilometry
Sparse R-CNN: End-to-End Object Detection With Learnable Proposals
Spatial Assembly Networks for Image Representation Learning
Spatial Feature Calibration and Temporal Fusion for Effective One-Stage Video Instance Segmentation
Spatially-Adaptive Pixelwise Networks for Fast Image Translation
Spatially-Invariant Style-Codes Controlled Makeup Transfer
Spatially-Varying Outdoor Lighting Estimation From Intrinsics
Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain
Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
Spatio-temporal Contrastive Domain Adaptation for Action Recognition
Spatiotemporal Contrastive Video Representation Learning
Spatiotemporal Registration for Event-Based Visual Odometry
SphereSR: 360° Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation
Spherical Confidence Learning for Face Recognition
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Spk2ImgNet: Learning To Reconstruct Dynamic Scene From Continuous Spike Stream
Spoken Moments: Learning Joint Audio-Visual Representations From Video Descriptions
SPSG: Self-Supervised Photometric Scene Generation From RGB-D Scans
Square Root Bundle Adjustment for Large-Scale Reconstruction
SRDAN: Scale-Aware and Range-Aware Domain Adaptation Network for Cross-Dataset 3D Object Detection
SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation
SSAN: Separable Self-Attention Network for Video Representation Learning
SSLayout360: Semi-Supervised Indoor Layout Estimation From 360deg Panorama
SSN: Soft Shadow Network for Image Compositing
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
ST3D: Self-Training for Unsupervised Domain Adaptation on 3D Object Detection
StablePose: Learning 6D Object Poses From Geometrically Stable Patches
Stable View Synthesis
STaR: Self-Supervised Tracking and Reconstruction of Rigid Objects in Motion With Neural Rendering
Stay Positive: Non-Negative Image Synthesis for Augmented Reality
StEP: Style-Based Encoder Pre-Training for Multi-Modal Image Synthesis

« prev Page 36/42 next »