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
Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
Multi-View Mesh Reconstruction with Neural Deferred Shading
Multi-View Transformer for 3D Visual Grounding
Multiview Transformers for Video Recognition
MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
Mutual Information-driven Pan-sharpening
Mutual Quantization for Cross-Modal Search with Noisy Labels
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
MVS2D: Efficient Multiview Stereo via Attention-Driven 2D Convolutions
NAN: Noise-Aware NeRFs for Burst-Denoising
NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction
Negative-Aware Attention Framework for Image-Text Matching
Neighborhood Attention Transformer
NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action
NeRF-Editing: Geometry Editing of Neural Radiance Fields
Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation
NeRFReN: Neural Radiance Fields with Reflections
NeRF-RPN: A general framework for object detection in NeRFs
NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction
Nested Collaborative Learning for Long-Tailed Visual Recognition
Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design
NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization
Neural 3D Scene Reconstruction with the Manhattan-world Assumption
Neural 3D Video Synthesis from Multi-view Video
Neural Architecture Search with Representation Mutual Information
Neural Collaborative Graph Machines for Table Structure Recognition
Neural Compression-Based Feature Learning for Video Restoration
Neural Convolutional Surfaces
Neural Data-Dependent Transform for Learned Image Compression
Neural Dependencies Emerging from Learning Massive Categories
NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
Neural Emotion Director: Speech-preserving semantic control of facial expressions in "in-the-wild" videos
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
Neural Fields as Learnable Kernels for 3D Reconstruction
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature
NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations
NeuralHOFusion: Neural Volumetric Rendering under Human-object Interactions
Neural Inertial Localization
NeuralLift-360: Lifting an in-the-Wild 2D Photo to A 3D Object with 360° Views
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection
Neural Mesh Simplification
Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture
Neural Point Light Fields
Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsampling
Neural Prior for Trajectory Estimation
Neural Rays for Occlusion-aware Image-based Rendering
Neural Recognition of Dashed Curves with Gestalt Law of Continuity
Neural RGB-D Surface Reconstruction

« prev Page 30/50 next »