CVPR 2022

2,477 papers

Top Research Directions

Research directions most represented by CVPR 2022 papers.

Generalizing from Synthetic Data to the Real World 41
Overcoming Local Receptive Field Constraints in Visual Models 38
Scaling Visual Attention Beyond Quadratic Complexity 36
Mitigating Error Propagation in Pseudo Labeling 28
Disentangling Attribute Control in Generative Models 23
Bypassing the Computational Bottleneck of Adversarial Training 23
Adversarial Training for Domain Invariant Representations 20
Addressing Inductive Bias Deficiency in Vision Transformers 19
Probabilistic Trajectory Forecasting for Autonomous Systems 18
Resolving Geometric Symmetry Ambiguity in 3D Pose Estimation 18
Decoupling Geometry and Appearance in Generative Models 17
Preserving Tiny Features Against Spatial Resolution Degradation 17
Resolving Depth Ambiguity in Monocular 3D Reconstruction 16
Cross Task Generalization in Image Restoration 15
The Representational Bottleneck of Frozen Foundation Models 15

Top Authors

AuthorPapers
Luc Van Gool24
Dacheng Tao20
Alan Yuille12
Dongdong Chen12
Jiaya Jia12
Antonio Torralba11
Jie Zhou11
Bernt Schiele10
Cewu Lu10
Errui Ding10
Jitendra Malik10
Yanwei Fu10
Yi Yang10
Chen Change Loy9
Fahad Shahbaz Khan9
Leonidas Guibas9
Minsu Cho9
Qi Tian9
Xian-Sheng Hua9
Xiaodan Liang9

Impactful Papers

Papers from CVPR 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
RU-Net: Regularized Unrolling Network for Scene Graph Generation
RUST: Latent Neural Scene Representations from Unposed Imagery
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Safe Self-Refinement for Transformer-based Domain Adaptation
Safe-Student for Safe Deep Semi-Supervised Learning with Unseen-Class Unlabeled Data
Salient-to-Broad Transition for Video Person Re-identification
Salvage of Supervision in Weakly Supervised Object Detection
SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation
SASIC: Stereo Image Compression with Latent Shifts and Stereo Attention
SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels
Scale-Equivalent Distillation for Semi-Supervised Object Detection
ScaleNet: A Shallow Architecture for Scale Estimation
Scaling Language-Image Pre-Training via Masking
Scaling Up Vision-Language Pretraining for Image Captioning
Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
Scaling Vision Transformers
Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
Scanline Homographies for Rolling-Shutter Plane Absolute Pose
SceneComposer: Any-Level Semantic Image Synthesis
Scene Consistency Representation Learning for Video Scene Segmentation
Scene Graph Expansion for Semantics-Guided Image Outpainting
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
SceneSqueezer: Learning to Compress Scene for Camera Relocalization
SCENIC: A JAX Library for Computer Vision Research and Beyond
ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
SCOTCH and SODA: A Transformer Video Shadow Detection Framework
Scribble-Supervised LiDAR Semantic Segmentation
SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation
Searching the Deployable Convolution Neural Networks for GPUs
Seeing a Rose in Five Thousand Ways
Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning
SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information
Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection
Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation
Segmenting across places: The need for fair transfer learning with satellite imagery
Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way
Selective-Supervised Contrastive Learning with Noisy Labels
Self-augmented Unpaired Image Dehazing via Density and Depth Decomposition
Self-Calibrated Efficient Transformer for Lightweight Super-Resolution
Self-Distillation from the Last Mini-Batch for Consistency Regularization
SelfD: Self-Learning Large-Scale Driving Policies From the Web
Self-Guided Diffusion Models

« prev Page 39/50 next »