This model implements EoMT (Encoder-only Mask Transformer) for universal image segmentation on the COCO panoptic dataset. It performs both semantic and instance segmentation in a unified framework, suitable for computer vision research and applications requiring detailed scene understanding. The large 640px variant balances accuracy and computational requirements for practical deployment.
In the Other AI space, Coco Panoptic Eomt Large 640 takes a focused approach. Accurately segmenting images into semantic and instance masks for panoptic scene understanding. Coco Panoptic Eomt Large 640 is an open-source project aimed at developers. The project is open source (MIT). It runs on the web and API.
Behind Coco Panoptic Eomt Large 640 is Mobile Perception Systems Lab, and it first shipped in 2025. The project is developed in the open on GitHub with 615 stars and 3 commits in the last 90 days. Key capabilities include Panoptic Segmentation, Image Segmentation, and Vision Transformer.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match