firstbacksecondback
308 Results
|
Poster
|
Wed 11:00 |
Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image Yu Zhao · Hao Fei · Xiangtai Li · Libo Qin · Jiayi Ji · Hongyuan Zhu · Meishan Zhang · Min Zhang · Jianguo Wei |
|
|
Poster
|
Thu 11:00 |
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching DONGZHI JIANG · Guanglu Song · Xiaoshi Wu · Renrui Zhang · Dazhong Shen · ZHUOFAN ZONG · Yu Liu · Hongsheng Li |
|
|
Poster
|
Wed 16:30 |
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models Xinchen Zhang · Ling Yang · YaQi Cai · Zhaochen Yu · Kai-Ni Wang · xie jiake · Ye Tian · Minkai Xu · Yong Tang · Yujiu Yang · Bin CUI |
|
|
Workshop
|
Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through f-divergence Minimization Haoyuan Sun · Bo Xia · Yongzhe Chang · Xueqian Wang |
||
|
Workshop
|
Generating Intermediate Representations for Compositional Text-To-Image Generation Ran Galun · Sagie Benaim |
||
|
Workshop
|
Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models Arash Mari Oriyad · Rezaei · Mahdieh Soleymani · Mohammad Hossein Rohban |
||
|
Affinity Event
|
Text-Image Concept Human Alignment Dataset and Metric Maria Alejandra Bravo |
||
|
Workshop
|
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty Xindi Wu · Dingli Yu · Yangsibo Huang · Olga Russakovsky · Sanjeev Arora |
||
|
Poster
|
Fri 11:00 |
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation Lianyu Pang · Jian Yin · Baoquan Zhao · Feize Wu · Fu Lee Wang · Qing Li · Xudong Mao |
|
|
Workshop
|
OC-CLIP : Object-centric Binding in Contrastive Language-Image Pretraining Rim Assouel · Pietro Astolfi · Florian Bordes · Michal Drozdzal · Adriana Romero |
||
|
Workshop
|
Sat 13:00 |
Localized Text-to-Image Generation For Free via Cross Attention Control Yutong He · Ruslan Salakhutdinov · J. Zico Kolter |
|
|
Poster
|
Thu 16:30 |
Generating compositional scenes via Text-to-image RGBA Instance Generation Alessandro Fontanella · Petru-Daniel Tudosiu · Yongxin Yang · Shifeng Zhang · Sarah Parisot |