ECCV 2024

2,499 papers

Top Research Directions

Research directions most represented by ECCV 2024 papers.

Mitigating Multi View Inconsistency in Generative 3D Modeling 46
Generalizing from Synthetic Data to the Real World 41
Aligning Global Semantics with Local Spatial Precision 28
Vertical Feature Collapse in Spatial Projections 23
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 23
Mitigating Error Propagation in Pseudo Labeling 22
Error Propagation in Monocular Depth Priors 21
Spatial Attention Masking in Generative Diffusion Models 21
The Computational Overhead of Generative Data Synthesis 21
Physics Constrained Generative Human Motion Synthesis 20
Overcoming the Static Scene Assumption 20
Accelerating Neural Scene Representations for Real Time Rendering 20
Resolving Mesh Interpenetration in 3D Reconstruction and Generation 19
Preserving Tiny Features Against Spatial Resolution Degradation 19
Disentangling Attribute Control in Generative Models 17

Top Authors

AuthorPapers
Marc Pollefeys19
Ziwei Liu16
Lei Zhang14
Luc Van Gool14
Yu Qiao13
Hongsheng Li12
Federico Tombari11
Ying Shan11
Jingdong Wang10
Abhinav Shrivastava9
Christian Rupprecht9
Daniel Barath9
Kuk-Jin Yoon9
Mubarak Shah9
Alan Yuille8
Andrea Vedaldi8
Cewu Lu8
Dahua Lin8
Daniel Cohen-Or8
Dimitris Samaras8

Impactful Papers

Papers from ECCV 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation
Weakly-Supervised Spatio-Temporal Video Grounding with Variational Cross-Modal Alignment
Weak-to-Strong Compositional Learning from Generative Models for Language-Based Object Detection
Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment
WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation
WeConvene: Learned Image Compression with Wavelet-Domain Convolution and Entropy Model
WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-Only Supervised Text Spotting
Weight Conditioning for Smooth Optimization of Neural Networks
Weighted Ensemble Models Are Strong Continual Learners
Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation
WHAC: World-Grounded Humans and Cameras
What Could Go Wrong? Discovering and Describing Failure Modes in Computer Vision
What's Wrong with the Absolute Trajectory Error?
When and How do negative prompts take effect?
When Fast Fourier Transform Meets Transformer for Image Restoration
When Pedestrian Detection Meets Multi-modal Learning: Generalist Model and Benchmark Dataset
"Where am I?" Scene Retrieval with Language
Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
WildRefer: 3D Object Localization in Large-Scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
WiMANS: A Benchmark Dataset for WiFi-Based Multi-user Activity Sensing
WindPoly: Polygonal Mesh Reconstruction via Winding Numbers
Within the Dynamic Context: Inertia-Aware 3D Human Modeling with Pose Sequence
WordRobe: Text-Guided Generation of Textured 3D Garments
WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation
WoVoGen: World Volume-Aware Diffusion for Controllable Multi-camera Driving Scene Generation
WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models
WRIM-Net: Wide-Ranging Information Mining Network for Visible-Infrared Person Re-identification
WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering
WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-Grained Spatial-Temporal Understanding
X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs
xGen-VideoSyn-1: High-Fidelity Text-to-Video Synthesis with Compressed Representations
X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-Modal Reasoning
X-Pose: Detecting Any Keypoints
XPSR: Cross-Modal Priors for Diffusion-Based Image Super-Resolution
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-person Multi-task Human-Centric Perception
You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video
Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems
Zero-Shot Detection of AI-Generated Images
Zero-Shot Image Feature Consensus with Deep Functional Maps
Zero-Shot Multi-object Scene Completion
Zero-Shot Object Counting with Good Exemplars
Zero-shot Text-guided Infinite Image Synthesis with LLM guidance
ZeST: Zero-Shot Material Transfer from a Single Image
ZigMa: A DiT-style Zigzag Mamba Diffusion Model
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model

« prev Page 50/50