ECCV - arXivDaily 期刊&会议

2407.21686 2024-08-01 cs.CV

Expressive Whole-Body 3D Gaussian Avatar

Gyeongsik Moon, Takaaki Shiratori, Shunsuke Saito

Comments Accepted to ECCV 2024. Project page: https://mks0601.github.io/ExAvatar/

2407.21654 2024-08-01 cs.CV

MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment

Anurag Das, Xinting Hu, Li Jiang, Bernt Schiele

Comments accepted at ECCV 2024

2407.21635 2024-08-01 cs.LG

MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction

Seongju Lee, Junseok Lee, Yeonguk Yu, Taeri Kim, Kyoobin Lee

Comments 19 pages, 12 figures, 7 tables, 8 pages of supplementary material. Paper accepted at ECCV 2024

2407.09033 2024-08-01 cs.CV

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

Byeonghyun Pak, Byeongju Woo, Sunghwan Kim, Dae-hwan Kim, Hoseong Kim

Comments ECCV 2024

2312.03048 2024-08-01 cs.CV

DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control

Yuru Jia, Lukas Hoyer, Shengyu Huang, Tianfu Wang, Luc Van Gool, Konrad Schindler, Anton Obukhov

Comments ECCV 2024, camera ready

2407.21448 2024-08-01 cs.CV

Accelerating Image Super-Resolution Networks with Pixel-Level Classification

Jinho Jeong, Jinwoo Kim, Younghyun Jo, Seon Joo Kim

Comments Accepted by ECCV 2024

2407.21381 2024-08-01 eess.IV cs.CV

Identity-Consistent Diffusion Network for Grading Knee Osteoarthritis Progression in Radiographic Imaging

Wenhua Wu, Kun Hu, Wenxi Yue, Wei Li, Milena Simic, Changyang Li, Wei Xiang, Zhiyong Wang

Comments Accepted by ECCV 2024

2407.21032 2024-08-01 cs.CV cs.AI

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion

Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee

Comments ECCV 2024. 56 pages, 24 figures. Caution: This paper contains discussions and examples related to harmful content, including text and images. Reader discretion is advised. Code is available at https://github.com/nannullna/safeguard-hfi

2407.18839 2024-08-01 cs.CV

Scalable Group Choreography via Variational Phase Manifold Learning

Nhat Le, Khoa Do, Xuan Bui, Tuong Do, Erman Tjiputra, Quang D. Tran, Anh Nguyen

Comments Accepted at ECCV 2024

2407.05586 2024-08-01 cs.CV

Dynamic Neural Radiance Field From Defocused Monocular Video

Xianrui Luo, Huiqiang Sun, Juewen Peng, Zhiguo Cao

Comments Accepted by ECCV 2024

2405.14841 2024-08-01 cs.CV

MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos

Yihong Sun, Bharath Hariharan

Comments ECCV 2024

2311.12751 2024-08-01 cs.CV cs.MM

Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching

Meng Chu, Zhedong Zheng, Wei Ji, Tingyu Wang, Tat-Seng Chua

Comments Accepted by ECCV 2024

2407.20727 2024-07-31 cs.CV

SceneTeller: Language-to-3D Scene Generation

Başak Melis Öcal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers

Comments ECCV'24 camera-ready version

2407.20542 2024-07-31 cs.CV cs.HC

HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimation

Wencan Cheng, Eunji Kim, Jong Hwan Ko

Comments Accepted as a conference paper to European Conference on Computer Vision (ECCV) 2024

2407.20341 2024-07-31 cs.CV cs.AI cs.CL cs.MM

BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues

Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Comments ECCV 2024

2407.20337 2024-07-31 cs.CV cs.AI cs.MM

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

Lorenzo Baraldi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Alessandro Nicolosi, Rita Cucchiara

Comments ECCV 2024

2407.19593 2024-07-31 cs.CV

Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture

ShahRukh Athar, Shunsuke Saito, Zhengyu Yang, Stanislav Pidhorsky, Chen Cao

Comments ECCV 2024

2403.07263 2024-07-31 cs.CV cs.LG stat.ML

Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction

Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann, Eric Nalisnick

Comments European Conference on Computer Vision (ECCV) 2024; 37 pages, 14 figures, 6 tables (incl. appendix)

2311.16937 2024-07-31 cs.CV

The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility

James A. D. Gardner, Evgenii Kashin, Bernhard Egger, William A. P. Smith

Comments Accepted to ECCV 2024

2407.20229 2024-07-30 cs.CV

Improving 2D Feature Representations by 3D-Aware Fine-Tuning

Yuanwen Yue, Anurag Das, Francis Engelmann, Siyu Tang, Jan Eric Lenssen

Comments ECCV 2024. Project page: https://ywyue.github.io/FiT3D

2407.20228 2024-07-30 cs.CV

FlexAttention for Efficient High-Resolution Vision-Language Models

Junyan Li, Delin Chen, Tianle Cai, Peihao Chen, Yining Hong, Zhenfang Chen, Yikang Shen, Chuang Gan

Comments Accepted by ECCV 2024

2407.20223 2024-07-30 cs.CV cs.RO

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

Ray Zhang, Zheming Zhou, Min Sun, Omid Ghasemalizadeh, Cheng-Hao Kuo, Ryan Eustice, Maani Ghaffari, Arnie Sen

Comments 10 pages, to be published in ECCV 2024

2407.19666 2024-07-30 cs.CV

Take A Step Back: Rethinking the Two Stages in Visual Reasoning

Mingyu Zhang, Jiting Cai, Mingyu Liu, Yue Xu, Cewu Lu, Yong-Lu Li

Comments ECCV 2024, Project page: https://mybearyzhang.github.io/projects/TwoStageReason/

2407.19471 2024-07-30 cs.CV

On the Evaluation Consistency of Attribution-based Explanations

Jiarui Duan, Haoling Li, Haofei Zhang, Hao Jiang, Mengqi Xue, Li Sun, Mingli Song, Jie Song

Comments Accepted as a conference paper by ECCV 2024

2407.19208 2024-07-30 cs.GR

WindPoly: Polygonal Mesh Reconstruction via Winding Numbers

Xin He, Chenlei Lv, Pengdi Huang, Hui Huang

Comments European Conference on Computer Vision (Proceedings of ECCV 2024)

2407.19014 2024-07-30 cs.CV

Sparse Refinement for Efficient High-Resolution Semantic Segmentation

Zhijian Liu, Zhuoyang Zhang, Samir Khaki, Shang Yang, Haotian Tang, Chenfeng Xu, Kurt Keutzer, Song Han

Comments ECCV 2024. The first two authors contributed equally to this work. Project page: https://sparserefine.mit.edu

2407.14726 2024-07-30 cs.CV cs.LG

MetaAug: Meta-Data Augmentation for Post-Training Quantization

Cuong Pham, Hoang Anh Dung, Cuong C. Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do

Comments Accepted by ECCV 2024

2405.05806 2024-07-30 cs.CV

MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation

Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Hongzhi Zhang, Lei Zhang, Wangmeng Zuo

Comments ECCV 2024. Our code can be found at https://github.com/csyxwei/MasterWeaver

2405.02771 2024-07-30 cs.CV cs.AI cs.LG

MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning

Vishal Nedungadi, Ankit Kariryaa, Stefan Oehmcke, Serge Belongie, Christian Igel, Nico Lang

Comments Accepted for ECCV 2024. Data and code: https://vishalned.github.io/mmearth Update arXiv v2 (ECCV): 1. Dataset fix: Removed duplicates and corrected ERA5 yearly statistics. 2. Data augmentation fix: Random crops are now aligned. 3. Test metrics fix: Metrics are now overall instead of mini-batch averages, matching GEO-Bench metrics. 4. Pretrained on MMEarth v001 & evaluated on GEO-Bench v1.0

2404.00995 2024-07-30 cs.CV

PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation

Jaejung Seol, Seojun Kim, Jaejun Yoo

Comments ECCV 2024