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
FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network
Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition
Feature Separation and Recalibration for Adversarial Robustness
Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers
FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
Federated Domain Generalization with Generalization Adjustment
Federated Generalized Category Discovery
Federated Incremental Semantic Segmentation
Federated Learning in Non-IID Settings Aided by Differentially Private Synthetic Data
Federated Learning with Data-Agnostic Distribution Fusion
FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation
FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction
Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation
Few-Shot Geometry-Aware Keypoint Localization
Few-Shot Non-Line-of-Sight Imaging with Signal-Surface Collaborative Regularization
Few-Shot Referring Relationships in Videos
Few-shot Semantic Image Synthesis with Class Affinity Transfer
FFCV: Accelerating Training by Removing Data Bottlenecks
FFF: Fragment-Guided Flexible Fitting for Building Complete Protein Structures
FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction
FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
Finding Geometric Models by Clustering in the Consensus Space
Fine-grained Audible Video Description
Fine-Grained Classification with Noisy Labels
Fine-Grained Face Swapping Via Regional GAN Inversion
Fine-grained Image-text Matching by Cross-modal Hard Aligning Network
Fine-tuned CLIP Models are Efficient Video Learners
Finetune like you pretrain: Improved finetuning of zero-shot vision models
FitMe: Deep Photorealistic 3D Morphable Model Avatars
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs
FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
FLEX: Full-Body Grasping Without Full-Body Grasps
Flexible-CGAN: Towards Precise 3D Dose Prediction in Radiotherapy
Flexible-Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy
FlexiViT: One Model for All Patch Sizes
FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
FlowGrad: Controlling the Output of Generative ODEs with Gradients
Flow Supervision for Deformable NeRF
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
Focused and Collaborative Feedback Integration for Interactive Image Segmentation
Focus On Details: Online Multi-Object Tracking with Diverse Fine-Grained Representation
Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
Fooling Polarization-based Vision using Locally Controllable Polarizing Projection
Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection

« prev Page 20/62 next »