1. [Publications](/publications) 2. Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models # Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models ![](/sites/default/files/styles/wide/public/publications/teaser%20%281%29%20copy.png?itok=okPirZm9) We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation, which unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary panoptic segmentation. Text-to-image diffusion models have the remarkable ability to generate high-quality images with diverse open-vocabulary language descriptions. This demonstrates that their internal representation space is highly correlated with open concepts in the real world. Text-image discriminative models like CLIP, on the other hand, are good at classifying images into open-vocabulary labels. We leverage the frozen internal representations of both these models to perform panoptic segmentation of any category in the wild. Our approach outperforms the previous state of the art by significant margins on both open-vocabulary panoptic and semantic segmentation tasks. In particular, with COCO training only, our method achieves 23.4 PQ and 30.0 mIoU on the ADE20K dataset, with 8.3 PQ and 7.9 mIoU absolute improvement over the previous state of the art. We open-source our code and models at . ## Authors Jiarui Xu (University of California at San Diego) [Sifei Liu](/person/sifei-liu) [Arash Vahdat](/person/arash-vahdat) [Wonmin Byeon](/person/wonmin-byeon) Xiaolong Wang (University of California at San Diego) [Shalini De Mello](/person/shalini-de-mello) ## Publication Date Saturday, June 17, 2023 ## Published in [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023](https://cvpr2023.thecvf.com/) ## Research Area [Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence) [Computer Vision](/research-area/computer-vision) [Generative AI](/research-area/generative-ai) ## External Links [Project Page](https://jerryxu.net/ODISE/) [Code](https://github.com/NVlabs/ODISE) [HuggingFace Demo](https://huggingface.co/spaces/xvjiarui/ODISE) [ArXiv](https://arxiv.org/abs/2303.04803) [Video](https://www.youtube.com/watch?v=eW2vF8o_7p0) ## Uploaded Files [Paper](https://d1qx31qr3h6wln.cloudfront.net/publications/2023_open_vocabulary_panoptic_segme-Camera-ready%20PDF.pdf "Open file in new window")4.6 MB [Supplementary](https://d1qx31qr3h6wln.cloudfront.net/publications/2023_open_vocabulary_panoptic_segme-Camera-ready%20Supplemental%20Material.pdf "Open file in new window")9.98 MB ## Award Hightlight top 10% ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .