Kaixin Cai — accepted AI-conference papers

2024

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model

Runhui Huang, Kaixin Cai, Jianhua Han, Xiaodan Liang*, Renjing Pei, Guansong Lu +3

ECCV 2024poster

"Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior work directly generates the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation

Kaixin Cai, Pengzhen Ren, Yi Zhu, Hang Xu, Jianzhuang Liu, Changlin Li +2

ICCV 2023poster

Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face difficulties in learning fine-grained semantic alignment at the pixel level and predicting accurate object masks. To add…

Cited by 19 PDF ↗Scholar ↗