One single model solves multiple perception tasks, on par with SOTA!
For academic use, this project is licensed under the 2-clause BSD License. For commercial use, please contact Chunhua Shen.
@misc{zhao2025diceptiongeneralistdiffusionmodel,
title={DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks},
author={Canyu Zhao and Mingyu Liu and Huanyi Zheng and Muzhi Zhu and Zhiyue Zhao and Hao Chen and Tong He and Chunhua Shen},
year={2025},
eprint={2502.17157},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2502.17157},
}