EdgeTAM is a lightweight variant of SAM 2, designed for on-device video segmentation and tracking. It is 22 times faster than SAM 2, reaching 16 FPS on the iPhone 15 Pro Max, and supports real-time video object segmentation and cross-frame tracking.

Computer VisionTransformers

UniPixel-3B is a unified multimodal large language model for pixel-level vision-language understanding, which can flexibly support various fine-grained tasks, including image/video segmentation, region understanding, and the novel PixelQA task. The model jointly requires object-centric reference, segmentation, and question answering in videos, achieving pixel-level visual reasoning capabilities.

MultimodalSafetensors

This model is a video language-guided reasoning segmentation model developed based on LLaVA-Phi-3-mini-4k-instruct, focusing on object segmentation tasks in videos.

MultimodalSafetensorsEnglish

PaliGemma 2 is a vision-language model (VLM) that combines the capabilities of the Gemma 2 model. It can process both image and text inputs simultaneously and generate text outputs, supporting multiple languages. It is suitable for various vision-language tasks such as image and short video captioning, visual question answering, text reading, object detection, and object segmentation.

MultimodalTransformers