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
Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation
Region-Aware Face Swapping
RegionCLIP: Region-based Language-Image Pretraining
Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
REGTR: End-to-end Point Cloud Correspondences with Transformers
Reinforced Structured State-Evolution for Vision-Language Navigation
Relative Pose from a Calibrated and an Uncalibrated Smartphone Image
Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
Relightable Neural Human Assets from Multi-view Gradient Illuminations
RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
Remember Intentions: Retrospective-Memory-based Trajectory Prediction
Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer
Removing Objects From Neural Radiance Fields
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
Rendering Nighttime Image Via Cascaded Color and Brightness Compensation
RendNet: Unified 2D/3D Recognizer with Latent Space Rendering
RePaint: Inpainting using Denoising Diffusion Probabilistic Models
Replacing Labeled Real-image Datasets with Auto-generated Contours
RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction
RepNet: Efficient On-Device Learning via Feature Reprogramming
Representation Compensation Networks for Continual Semantic Segmentation
Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting
Representing 3D Shapes with Probabilistic Directed Distance Fields
Reproducible Scaling Laws for Contrastive Language-Image Learning
ResFormer: Scaling ViTs with Multi-Resolution Training
Residual Degradation Learning Unfolding Framework with Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging
Residual Feature Pyramid Network for Enhancement of Vascular Patterns
Residual Local Feature Network for Efficient Super-Resolution
ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning
RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs
Restormer: Efficient Transformer for High-Resolution Image Restoration
ReSTR: Convolution-free Referring Image Segmentation Using Transformers
Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning
Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation
Rethinking Controllable Variational Autoencoders
Rethinking Deep Face Restoration
Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
Rethinking Efficient Lane Detection via Curve Modeling
Rethinking Image Cropping: Exploring Diverse Compositions from Global Views
Rethinking Minimal Sufficient Representation in Contrastive Learning
Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection
Rethinking Semantic Segmentation: A Prototype View
Rethinking Spatial Invariance of Convolutional Networks for Object Counting
Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views
Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Rethinking Visual Geo-localization for Large-Scale Applications

« prev Page 37/50 next »