Fully Sparse 3D Occupancy Prediction
Comments Accepted to ECCV 2024. Code: https://github.com/MCG-NJU/SparseOcc
期刊&会议
ECCV
European Conference on Computer Vision · 会议 · Computer Vision
Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization
Comments Accepted at ECCV 2024
Fast View Synthesis of Casual Videos with Soup-of-Planes
Comments Accepted to ECCV 2024. Project page: https://casual-fvs.github.io/
Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
Journal ref ECCV 2024
Region-centric Image-Language Pretraining for Open-Vocabulary Detection
Comments ECCV 2024, project page at https://github.com/google-research/google-research/tree/master/fvlm/dito
Decoupling Common and Unique Representations for Multimodal Self-supervised Learning
Comments Accepted to ECCV 2024. 27 pages, 8 figures
GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition
Comments Accepted by ECCV 2024
Training-Free Model Merging for Multi-target Domain Adaptation
Comments Accepted to ECCV 2024
SegPoint: Segment Any Point Cloud via Large Language Model
Comments ECCV 2024, Project Page: https://heshuting555.github.io/SegPoint
MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References
Comments Accepted to ECCV 2024; Project Page: see https://boelukas.github.io/mariner/
Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models
Comments ECCV 2024
Training-free Composite Scene Generation for Layout-to-Image Synthesis
Comments ECCV 2024
MeshFeat: Multi-Resolution Features for Neural Fields on Meshes
Comments To appear at European Conference on Computer Vision (ECCV), 2024
Robust Calibration of Large Vision-Language Adapters
Comments ECCV 2024
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
Comments ECCV 2024
FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures
Comments Accepted to International Journal of Computer Vision. Extended version of ECCV 2022 paper at arXiv:2207.10392
SCAPE: A Simple and Strong Category-Agnostic Pose Estimator
Comments Accepted to ECCV 2024. Code is available at https://github.com/tiny-smart/SCAPE
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
Comments ECCV 2024
BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models
Comments Accepted at ECCV 2024. [Project Pages] https://beafbench.github.io/
FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions
Comments Accepted to ECCV 2024
OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction
Comments Accepted in ECCV 2024
Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation
Journal ref ECCV 2024
UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt
Comments Accepted by ECCV 2024
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
Comments ECCV 2024. Project page: https://feint6k.github.io
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
Comments Work Accepted for Publication at ECCV 2024
SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
Comments ECCV 2024
AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Comments Accepted by ECCV 2024; Project page: https://lzhxmu.github.io/accdiffusion/accdiffusion.html
Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
Comments This is the preprint version of our paper and supplemental material to appear in ECCV 2024
SRPose: Two-view Relative Pose Estimation with Sparse Keypoints
Comments 30 pages, 11 figures, to be published in ECCV 2024
Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
Comments Accepted by ECCV 2024
