CVPR 2023

3,088 papers

Top Research Directions

Research directions most represented by CVPR 2023 papers.

Generalizing from Synthetic Data to the Real World 39
Aligning Global Semantics with Local Spatial Precision 34
Mitigating Error Propagation in Pseudo Labeling 32
Accelerating Neural Scene Representations for Real Time Rendering 23
Mitigating Multi View Inconsistency in Generative 3D Modeling 22
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 22
Overcoming the Static Scene Assumption 21
Exploiting Temporal Redundancy in Video Neural Networks 21
Material Lighting Disentanglement for 3D Reconstruction 21
Bypassing the Computational Bottleneck of Adversarial Training 21
Resolving Shape Radiance Ambiguity in Sparse View Reconstruction 20
Overcoming the Iterative Inference Latency of Diffusion Models 19
Tri-Plane Feature Representations for 3D Deep Learning 18
Deep Learning on Unstructured 3D Point Clouds 17
Resolving Depth Ambiguity in Monocular 3D Reconstruction 17

Top Authors

AuthorPapers
Yu Qiao23
Ying Shan19
Luc Van Gool15
Yi-Zhe Song14
Yongdong Zhang14
Dacheng Tao13
Zhiwei Xiong13
Hongsheng Li12
Jiajun Wu12
Leonidas Guibas12
Michael J. Black12
Yi Yang12
Jie Zhou11
Otmar Hilliges11
Wanli Ouyang11
Yu-Gang Jiang11
Deva Ramanan10
Fahad Shahbaz Khan10
Han Hu10
Jiaya Jia10

Impactful Papers

Papers from CVPR 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension
Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
Regressor-Segmenter Mutual Prompt Learning for Crowd Counting
Regularization of polynomial networks for image recognition
Regularized Vector Quantization for Tokenized Image Synthesis
Regularize implicit neural representation by itself
Regularizing Second-Order Influences for Continual Learning
Reinforcement Learning-Based Black-Box Model Inversion Attacks
Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild
Relational Context Learning for Human-Object Interaction Detection
Relational Space-Time Query in Long-Form Videos
Reliability in Semantic Segmentation: Are we on the Right Track?
Reliable and Interpretable Personalized Federated Learning
Relightable and Animatable Neural Avatar from Sparse-View Video
Relightable Gaussian Codec Avatars
RelightableHands: Efficient Neural Relighting of Articulated Hand Models
Relightable Neural Human Assets from Multi-view Gradient Illuminations
Relightful Harmonization: Lighting-aware Portrait Background Replacement
ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects
Removing Objects From Neural Radiance Fields
Renderable Neural Radiance Map for Visual Navigation
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction
Representation Learning for Visual Object Tracking by Masked Appearance Transfer
Representing Volumetric Videos as Dynamic MLP Maps
Reproducible Scaling Laws for Contrastive Language-Image Learning
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
ResFormer: Scaling ViTs with Multi-Resolution Training
Residual Degradation Learning Unfolding Framework with Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging
Resource-Efficient RGBD Aerial Tracking
Restoration by Generation with Constrained Priors
Restoration of Hand-Drawn Architectural Drawings using Latent Space Mapping with Degradation Generator
ReTAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Rethinking Boundary Discontinuity Problem for Oriented Object Detection
Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment
Rethinking Feature-based Knowledge Distillation for Face Recognition
Re-Thinking Federated Active Learning Based on Inter-Class Diversity
Rethinking Federated Learning with Domain Shift: A Prototype View
Rethinking Few-Shot Medical Segmentation: A Vector Quantization View
Rethinking Gradient Projection Continual Learning: Stability/Plasticity Feature Space Decoupling
Rethinking Image Super Resolution from Long-Tailed Distribution Learning Perspective
Re-Thinking Model Inversion Attacks Against Deep Neural Networks
Rethinking Optical Flow from Geometric Matching Consistent Perspective
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation
Rethinking the Correlation in Few-Shot Segmentation: A Buoys View
Rethinking the Evaluation Protocol of Domain Generalization
Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

« prev Page 47/62 next »