CVPR 2024

2,857 papers

Top Research Directions

Research directions most represented by CVPR 2024 papers.

Mitigating Multi View Inconsistency in Generative 3D Modeling 71
Generalizing from Synthetic Data to the Real World 50
Aligning Global Semantics with Local Spatial Precision 41
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 36
Physics Constrained Generative Human Motion Synthesis 34
Spatial Attention Masking in Generative Diffusion Models 32
Overcoming the Static Scene Assumption 27
Material Lighting Disentanglement for 3D Reconstruction 27
Reconstructing Complete Geometry from Partial Point Clouds 27
Overcoming the Iterative Inference Latency of Diffusion Models 26
Visual Grounding and Hallucination in Vision Language Models 25
The Computational Overhead of Generative Data Synthesis 25
Accelerating Neural Scene Representations for Real Time Rendering 24
Resolving Mesh Interpenetration in 3D Reconstruction and Generation 23
Exploiting Temporal Redundancy in Video Neural Networks 22

Top Authors

AuthorPapers
Yu Qiao25
Ying Shan21
Marc Pollefeys16
Ziwei Liu16
Ming-Hsuan Yang15
Luc Van Gool13
Yi Yang13
Boxin Shi12
Dahua Lin12
Michael J. Black12
Tao Xiang11
Varun Jampani11
Yebin Liu11
Bernard Ghanem10
Fahad Shahbaz Khan10
Hengshuang Zhao10
Yi-Zhe Song10
Bo Dai9
Chen Change Loy9
Daniel Cremers9

Impactful Papers

Papers from CVPR 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
EfficientDreamer: High-Fidelity and Stable 3D Creation via Orthogonal-view Diffusion Priors
Efficient Feature Extraction and Late Fusion Strategy for Audiovisual Emotional Mimicry Intensity Estimation
Efficient Hyperparameter Optimization with Adaptive Fidelity Identification
Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed
Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization
Efficient Meshflow and Optical Flow Estimation from Event Cameras
Efficient Model Stealing Defense with Noise Transition Matrix
Efficient Multi-Scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring
Efficient Multitask Dense Predictor via Binarization
Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Efficient Scene Recovery Using Luminous Flux Prior
Efficient Solution of Point-Line Absolute Pose
Efficient Stitchable Task Adaptation
Efficient Test-Time Adaptation of Vision-Language Models
Efficient Vision-Language Pre-Training by Cluster Masking
EFHQ: Multi-Purpose ExtremePose-Face-HQ Dataset
EFormer: Enhanced Transformer Towards Semantic-Contour Features of Foreground for Portraits Matting
Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World
EgoGen: An Egocentric Synthetic Data Generator
EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models
E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator
EGTR: Extracting Graph from Transformer for Scene Graph Generation
ElasticDiffusion: Training-Free Arbitrary Size Image Generation Through Global-Local Content Separation
Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion
ELSA: Exploiting Layer-wise N: M Sparsity for Vision Transformer Acceleration
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion
EMCAD: Efficient Multi-Scale Convolutional Attention Decoding for Medical Image Segmentation
Emergent Open-Vocabulary Semantic Segmentation from Off-the-Shelf Vision-Language Models
EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models
EMOPortraits: Emotion-Enhanced Multimodal One-Shot Head Avatars
Emotional Speech-Driven 3D Body Animation via Disentangled Latent Diffusion
EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance
Emu Edit: Precise Image Editing via Recognition and Generation Tasks
En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data
Endow SAM with Keen Eyes: Temporal-Spatial Prompt Learning for Video Camouflaged Object Detection
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences
Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors
Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair
Enhancing Multimodal Cooperation via Sample-Level Modality Valuation

« prev Page 16/58 next »