Reliable Fidelity and Diversity Metrics for Generative Models
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments First two authors have contributed equally; ICML 2020 accepted
视觉与机器人
图像生成、文生图、图像编辑、扩散模型和可控生成。
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments First two authors have contributed equally; ICML 2020 accepted
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments Accepted to CVPR 2020
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments 17 pages, 9 figures, pre-submmited to cvpr2019
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments 13 pages
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments AAAI 2020 Meta-Eval
专题命中 图像生成评测 :image synthesis(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments https://hype.stanford.edu
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments Video: https://youtu.be/x2g48Q2I2ZQ
专题命中 图像生成评测 :image editing(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments 10 pages, 5 figures
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments Project page: http://www.weixiushen.com/project/Awesome_FGIA/Awesome_FGIA.html. arXiv admin note: text overlap with arXiv:1902.06068 by other authors
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments This paper appears at CVPR 2019 Weakly Supervised Learning for Real-World Computer Vision Applications (LID) Workshop
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
专题命中 图像生成评测 :diffusion(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments Neural Information Processing Systems (NeurIPS) 2018
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments Wenqi Li and Eli Gibson contributed equally to this work. M. Jorge Cardoso and Tom Vercauteren contributed equally to this work. 26 pages, 6 figures; Update includes additional applications, updated author list and formatting for journal submission
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments 22 pages, 14 figures
专题命中 图像生成评测 :diffusion(abstract);分类 cs.CV
Comments 29th Annual Conference of the IEEE Engineering in Medicine and Biology Society - EMBC 2007
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Journal ref Color and Imaging Conference, Volume 2015, Number 1, October 2015, pp. 186-190(5)
专题命中 图像生成评测 :image synthesis(abstract);分类 cs.CV
专题命中 图像生成评测 :image generation(abstract);分类 cs.CV
Comments 10 pages, 7 figures. Appearing in Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS) 2016, Cadiz, Spain. JMLR: W&CP volume 41
专题命中 图像生成评测 :image editing(abstract);分类 cs.CV
Comments The manuscript was submitted to a conference. Due to anonymous review policy by the conference, I'd like to withdraw it temporarily
Journal ref This is a revised version of our submissions to CVPR 2012, SIGRAPH Asia 2012, and CVPR 2013;
专题命中 图像生成评测 :diffusion(abstract);分类 cs.CV
SoftVTBench:面向可变形物体操作的形变感知视觉-触觉数据集与基准
机构 * Tuojing Intelligence(拓境智能) ; Tsinghua University(清华大学) ; Southeast University(东南大学) ; Stevens Institute of Technology(斯蒂文斯理工学院) ; The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) ; University of Manchester(曼彻斯特大学) ; Simple AI ; Imperial College London(帝国理工学院) ; Carnegie Mellon University(卡内基梅隆大学) ; Zhejiang University(浙江大学) ; Beihang University(北京航空航天大学) ; The University of Hong Kong(香港大学)
专题命中 图像生成评测 :diffusion(abstract)
AI总结 本研究推出SoftVTBench视觉-触觉数据集与基准,定义形变感知成功率(DSR),发现触觉信息本身未必提升多模态融合,为可变形物体操作的物理交互研究提供资源。
RETO:一种增强旋转的Transformer操作符用于汽车气动性能的高保真预测
机构 * Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology(南方科技大学机械与航空航天工程系) ; Shenzhen Key Laboratory of Complex Aerospace Flows, Southern University of Science and Technology(深圳复杂航空航天流动重点实验室) ; Ningbo Key Laboratory of Advanced Manufacturing Simulation, Eastern Institute of Technology(宁波先进制造模拟重点实验室) ; Shenzhen Tenfong Science and Technology Co., Ltd.(深圳天丰科技有限公司)
专题命中 图像生成评测 :diffusion(abstract)
AI总结 本文提出RETO操作符,通过双阶段空间意识机制提升汽车气动预测精度,实验显示其在ShapeNet和DrivAerML数据集上均优于现有方法。
专题命中 图像生成评测 :image generation(abstract)
Comments 23 pages
Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), pages 27572-27595