no code implementations • 28 Oct 2024 • Yiyang Guo, Ruizhe Li, Mude Hui, Hanzhong Guo, Chen Zhang, Chuangjian Cai, Le Wan, Shangfei Wang
Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication.
1 code implementation • 8 Oct 2024 • Jiawei Mao, Xiaoke Huang, Yunfei Xie, Yuanqi Chang, Mude Hui, Bingjie Xu, Yuyin Zhou
Specifically, we propose an iterative paradigm to refine each generated image, leveraging both the text prompt and all generated images from the previous iteration.
no code implementations • 12 Jun 2024 • Xianhang Li, Haoqin Tu, Mude Hui, Zeyu Wang, Bingchen Zhao, Junfei Xiao, Sucheng Ren, Jieru Mei, Qing Liu, Huangjie Zheng, Yuyin Zhou, Cihang Xie
For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks.
Ranked #96 on Visual Question Answering on MM-Vet
no code implementations • 15 Apr 2024 • Mude Hui, Siwei Yang, Bingchen Zhao, Yichun Shi, Heng Wang, Peng Wang, Yuyin Zhou, Cihang Xie
This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200, 000 edits.
1 code implementation • CVPR 2024 • Mude Hui, Zihao Wei, Hongru Zhu, Fei Xia, Yuyin Zhou
This strategy enriches the diffusion process with structured 3D information, enhancing detail and reducing noise in localized 2D images.
no code implementations • CVPR 2023 • Mude Hui, Zhizheng Zhang, Xiaoyi Zhang, Wenxuan Xie, Yuwang Wang, Yan Lu
Since different attributes have their individual semantics and characteristics, we propose to decouple the diffusion processes for them to improve the diversity of training samples and learn the reverse process jointly to exploit global-scope contexts for facilitating generation.