ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement
Comments 14 pages, 13 figures, to be published in ICCV 2025
期刊&会议
International Conference on Computer Vision · 会议 · Computer Vision
Comments 14 pages, 13 figures, to be published in ICCV 2025
机构 * NVIDIA ; Osaka University(大阪大学) ; UC Berkeley(加州大学伯克利分校) ; Stanford University(斯坦福大学)
Comments ICCV 2025
机构 * ETH Zurich, Switzerland(苏黎世联邦理工学院) ; Faculty of Electrical Engineering, Czech Technical University in Prague(布拉格捷克技术大学电子工程学院) ; Hover Inc., USA(Hover公司)
Comments ICCV 2025 Highlight
机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University(中国教育部多媒体可信感知与高效计算重点实验室,厦门大学) ; School of Informatics, Xiamen University(厦门大学信息学院) ; Shenzhen University(深圳大学) ; Guangdong University of Technology(广东技术大学) ; Hong Kong Baptist University(香港 Baptist 大学) ; CAIR, HKISI, CAS(中国科学院CAS HKISI CAIR) ; MAIS, CASIA(中国科学院CASIA MAIS)
Comments Accepted by ICCV 2025
机构 * TU Delft(代尔夫特理工大学) ; CMU(卡内基梅隆大学)
Comments Accepted at ICCV 2025 Workshop CrocoDL
机构 * National Taiwan University(国立台湾大学) ; Qualcomm Technologies, Inc.(高通技术公司)
Journal ref ICCV-2025
机构 * Australian Institute for Machine Learning(澳大利亚机器学习研究所) ; The University of Adelaide(阿德莱德大学) ; Intel Labs(英特尔实验室)
Comments 13 pages, accepted in ICCV 2025 Workshop on Neuromorphic Vision (NeVI)
机构 * School of Computing, KAIST, Republic of Korea(韩国科学技术院计算机学院)
Comments Arxiv version of ICCV 2025 paper (3rd version)
机构 * Australian Institute for Machine Learning, University of Adelaide(澳大利亚机器学习研究所,阿德莱德大学)
Comments ICCV 2025
机构 * Tianjin University(天津大学) ; Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) ; Tencent Hunyuan(腾讯文言) ; Tencent AI Lab(腾讯AI实验室)
Comments ICCV 2025
机构 * The University of Hong Kong(香港大学) ; Kling Team, Kuaishou Technology(快手科技 Kling 团队) ; Lingnan University(岭大)
Comments ICCV 2025
机构 * Auburn University(亚伯拉罕大学) ; University of Alabama at Birmingham(阿拉巴马大学伯明翰分校)
Comments This paper has been accepted by TrustFM: Workshop on Trustworthy Foundation Models in conjunction with ICCV 2025