 ReCo: Region-Controlled Text-to-Image GenerationComputer Vision and Pattern Recognition (CVPR), 2022 |
 SceneComposer: Any-Level Semantic Image SynthesisComputer Vision and Pattern Recognition (CVPR), 2022 |
 Learning to Model Multimodal Semantic Alignment for Story VisualizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 DiffEdit: Diffusion-based semantic image editing with mask guidanceInternational Conference on Learning Representations (ICLR), 2022 |
 Memory-Driven Text-to-Image GenerationBritish Machine Vision Conference (BMVC), 2022 |
 Word-Level Fine-Grained Story VisualizationEuropean Conference on Computer Vision (ECCV), 2022 |
 DT2I: Dense Text-to-Image Generation from Region DescriptionsInternational Conference on Artificial Neural Networks (ICANN), 2022 |
