TU2.L5.3

Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models

Kuluhan Binici, SAP, National University of Singapore, Singapore; Cihan Acar, Institute for Infocomm Research (I2R), A*STAR, Singapore; Shivam Aggarwal, National University of Singapore, Singapore; Siying Liu, Institute for Infocomm Research (I2R), A*STAR, Singapore; Tulika Mitra, National University of Singapore, Singapore
Session:
TU2.L5: Generative Image Models: Methods, Datasets, and Applications 1 Lecture
Track:
Special Sessions
Location:
Room 3 (SS1)
Presentation Time:
Tue, 16 Sep, 10:30 - 10:45 Anchorage Time (UTC -8)
Session Chair:
Chia-Wen Lin, National Tsing Hua University
Presentation
Discussion
Resources
No resources available.
Session TU2.L5
TU2.L5.1: Compressing Human Body Video with Interactive Semantics: A Generative Approach
Bolin Chen, Shanzhi Yin, Hanwei Zhu, Lingyu Zhu, Zihan Zhang, City University of Hong Kong, China; Jie Chen, Ru-Ling Liao, Alibaba Group, China; Shiqi Wang, City University of Hong Kong, China; Yan Ye, Alibaba Group, United States
TU2.L5.2: DETECTING AND MITIGATING INCOHERENT INPUT OF LATENT DIFFUSION MODELS
Christopher Kuhn, Sureel Inc., Germany; Boğaç Ünver, Technical University of Munich, Germany; Diego Vera, Christoph Burgmair, Tamay Aykut, Sureel Inc., Germany
TU2.L5.3: Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
Kuluhan Binici, SAP, National University of Singapore, Singapore; Cihan Acar, Institute for Infocomm Research (I2R), A*STAR, Singapore; Shivam Aggarwal, National University of Singapore, Singapore; Siying Liu, Institute for Infocomm Research (I2R), A*STAR, Singapore; Tulika Mitra, National University of Singapore, Singapore
TU2.L5.4: Enhancing Image Deraining through VLM-Based Data Refinement and Classification
Shih-Jui Liang, Zihao Chen, National Chengchi University, Taiwan; Jun-Cheng Chen, Academia Sinica, Taiwan; Yan-Tsung Peng, National Chengchi University, Taiwan
TU2.L5.5: Enabling Controllable, Identity Preserving, Non-Rigid Edits in Human-Centric Images
Nikolai Warner, Jack Kolb, Georgia Tech, United States; Meera Hahn, Jonathan Huang, Vighnesh Birodkar, Google, United States; Irfan Essa, Georgia Tech, United States
TU2.L5.6: GARMENT DE-WARPING FOR VIRTUAL TRY-ON IN THE WILD
Yu Gu, Jiexuan Zhang, Qian Wang, Jian Zhang, Peking University, China
Contacts