zero-shot-segmentation

Segment Anything in High Quality [NeurIPS 2023]

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)

ZIM: Zero-Shot Image Matting for Anything

[ICCV 2023 R6D] PyTorch implementation of CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything and DINOv2

SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation (3DV 2025)

[CVPR 2025] Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"

Multi-Aspect Vision Language Pretraining - CVPR2024

Image Instance Segmentation - Zero Shot - OpenAI's CLIP + Meta's SAM

Official code for "DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut", NeurIPS 2024

EfficientSAM + YOLO World base model for use with Autodistill.

(SegmentedOWLv2) is a powerful command-line tool for text-prompted object segmentation for video and images.

This repository contains the source code and reports for a AR-based Robotic Control System project, developed as part of the SUPSI Project Course. The project leverages Augmented Reality, Machine Learning, and Advanced Robotics to create an intuitive, efficient, and human-centric industrial automation solution.

Implementation of Zero-shot Anomaly Segmentation (ZSAS) Model based on Dynamic Object-aware Tagging (DOT) Prompt

Segment Anything in High Quality

Explore Segment Anything Model 2 (SAM 2) for advanced visual segmentation in images and videos. Check out the code and demo on GitHub! 🐙🌟