IVMSP-P1.10
No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
Mohammad Hossein Sameti, Amir M. Mansourian, Arash Marioriyad, Soheil Fadaee Oshyani, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah, Sharif University of Technology, Iran (Islamic Republic of)
Session:
IVMSP-P1: Image Generation Poster
Track:
Image, Video and Multidimensional Signal Processing [IV]
Location:
Poster Area 15
Presentation Time:
Tue, 5 May, 14:00 - 16:00
Presentation
Discussion
Resources
No resources available.
Session IVMSP-P1
IVMSP-P1.1: DREAMVAR: TAMING REINFORCED VISUAL AUTOREGRESSIVE MODEL FOR HIGH-FIDELITY SUBJECT-DRIVEN IMAGE GENERATION
Xin Jiang, Nanjing University of Science and Technology, China; Jingwen Chen, Yehao Li, Yingwei Pan, Hidream.ai, China; Kezhou Chen, University of Science and Technology of China, China; Zechao Li, Nanjing University of Science and Technology, China; Ting Yao, Tao Mei, Hidream.ai, China
IVMSP-P1.2: DiPaS-Bridge: Towards Paired-Guided Diverse Generation for Urban Layouts
Xiaohang Dong, Nankai university, China; Hualong Yu, Nankai University, China; Xu Zhang, Jianye Wang, Nankai university, China; Qicheng Li, Nankai University, China
IVMSP-P1.3: GIFT: A Generative Imagined Fine-Tuning Framework for Visual Place Recognition
Zhenyu Xu, Yudian Zheng, University of Macau, China; Qieshi Zhang, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China; Chi-Man Pun, University of Macau, Macao
IVMSP-P1.4: GEN3D:GENERATING DOMAIN-FREE 3D SCENES FROM A SINGLE IMAGE
Yuxin Zhang, Ziyu Lu, Hongbo Duan, Keyu Fan, Tsinghua university, China; Pengting Luo, Peiyu Zhuang, Huawei, China; Mengyu Yang, Houde Liu, Tsinghua university, China
IVMSP-P1.5: PPFC: A REINFORCEMENT LEARNING-BASED FEEDBACK FRAMEWORK FOR HIGH-FIDELITY CHINESE POETRY-TO-IMAGE GENERATION
Wang Chongyu, Liu Yu, Li Tianyu, Fan Chunxiao, Wu Yuexin, Beijing University of Posts and Telecommunications, Beijing, China, China
IVMSP-P1.6: H3GM: HISTORY-GUIDED GLOBAL GEOMETRIC METRIC FOR SINGLE IMAGE TO 3D SCENE GENERATION
Yuki Katayama, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
IVMSP-P1.7: 3D-Aware Shadow Generation for Composite Image
Yanping Fu, Jiazheng Tao, Chenpei Li, Shaojie Zhang, Dengdi Sun, Haifeng Zhao, Anhui University, China
IVMSP-P1.8: MISA: MULTI-STAGE INTERACTIVE SELF-ATTENTION FOR CONSISTENT SUBJECT-DRIVEN TEXT-TO-IMAGE GENERATION
shouxin Tang, yuanbo Li, ziyi zhang, cong Hu, JiangNanUniversity, China
IVMSP-P1.9: ASSESSING IDENTITY LEAKAGE IN TALKING FACE GENERATION: METRICS AND EVALUATION FRAMEWORK
Dogucan Yaman, Fevziye Irem Eyiokur, Karlsruhe Institute of Technology, Germany; Hazım Kemal Ekenel, Istanbul Technical University, Türkiye; Alexander Waibel, Karlsruhe Institute of Technology, Germany
IVMSP-P1.10: No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
Mohammad Hossein Sameti, Amir M. Mansourian, Arash Marioriyad, Soheil Fadaee Oshyani, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah, Sharif University of Technology, Iran (Islamic Republic of)
Contacts