MMSP-L8.5
Self-Attention Decomposition for Training Free Diffusion Editing
Tharun Anand, Samsung, India; Mohammad Hassan Vali, Arno Solin, Aalto University, Finland; Green Rosh, B H Pawan Prasad, Samsung, India
Session:
MMSP-L8: High-Fidelity Multimedia Editing with Diffusion Models Oral
Track:
Multimedia Signal Processing [MM]
Location:
Room 131+132
Presentation Time:
Thu, 7 May, 17:50 - 18:10
Presentation
Discussion
Resources
No resources available.
Session MMSP-L8
MMSP-L8.1: GalaxyEdit: Large Scale Image Editing Dataset with Enhanced Diffusion Adapter
Rohan Jaiswal, Aniruddha Bala, Siddharth Roheda, Rohit Chowdhury, Samsung R&D Institute, Bangalore, India
MMSP-L8.2: Fast and Accurate Text-to-Motion Generation through Discrete-Guided Continuous Modeling
Liping Zhu, Yichen Ge, Chengyang Li, Jian Gao, China University of Petroleum (Beijing), China; Hao Li, Xidian University, China
MMSP-L8.3: ACTIVE-EDIT: HIGH-FIDELITY 3D EDITING FROM A HANDFUL OF TASK-RELEVANT
Yuhang You, Xinpeng Liu, Shenzhen Graduate school, Peking University, China; Weimin Zhang, Shiqiang Long, Guangdong Bohua UHD Innovation Center Co.，Ltd., China; Ge Li, Shenzhen Graduate school, Peking University, China
MMSP-L8.4: Stylized Text-to-Motion Synthesis via Multi-condition Latent Diffusion
Fanglu Xie, Tsukasa Shiota, Motohiro Takagi, NTT, Inc., Japan; Edgar Simo-Serra, Waseda University, Japan
MMSP-L8.5: Self-Attention Decomposition for Training Free Diffusion Editing
Tharun Anand, Samsung, India; Mohammad Hassan Vali, Arno Solin, Aalto University, Finland; Green Rosh, B H Pawan Prasad, Samsung, India
MMSP-L8.6: PARAEDIT: UNIFYING PARALLEL TRANSPORT AND GENERATIVE FLOWS FOR HIGH-FIDELITY IMAGE EDITING
Yuan Zhou, Jinyoung Wen, Yuyang Hong, Kun Ding, Institute of Automation, Chinese Academy of Sciences, China; Yan Zhang, Guangwen Yang, Tsinghua University, China; Shiming Xiang, Institute of Automation, Chinese Academy of Sciences, China
Contacts