[CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation
[Colab Demo Code] OneFormer: One Transformer to Rule Universal Image Segmentation.
Hugging Face Object Detection, Instance Segmentation, Semantic Segmentation, Panoptic Segmentation in PyTorch Fine-tuning.
This project combines segmentation model and logic tensor network to realize the reasoning of object relationship in images and improve image content analysis through first-order logic formula and multi-layer perceptron network.
A web-based object segmentation app using HuggingFace transformers (SAM, SegFormer, Mask2Former, OneFormer). Supports image, video, and live webcam segmentation with a FastAPI backend and vanilla JS frontend.
To associate your repository with the oneformer topic, visit your repo's landing page and select "manage topics."