Abstract: Image segmentation is a fundamental and critical task in computer vision, with applications across various domains, such as medical imaging, autonomous driving, and satellite image analysis.

We present SegLLM, a novel multi-round interactive segmentation model that leverages conversational memory of both visual and textual outputs to reason over previously segmented objects and past ...

Abstract: Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to ...

Turn photos into 3D with Meta's SAM 3D, using SAM 2 masks and Gaussian splatting, so you can build assets quickly for ...