mask2former

SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch.

[CVPR 2024] Official Implementation of Collaborating Foundation models for Domain Generalized Semantic Segmentation

The official code repository for paper "Rethinking the Encoding of Satellite Image Time Series".

Windows GUI pipeline for turning 360° video into scale-calibrated 3DGS training assets: frame review, YOLO/SAM masks, Metashape/SphereSfM/COLMAP Rig, AprilTag scale calibration, and LichtFeld/Postshot/Brush exports.

AgriSegment — A multi-modal plant segmentation suite for agricultural research. It offers four FastAPI-powered tools—Hybrid (SegFormer + SAM), Interactive (real-time SAM), Semantic (batch SegFormer), and Panoptic (Mask2Former)—making AI-driven plant segmentation accessible to non-programmers.

Separate mask2former from framework

Fine-tuning Mask2Former on the FoodSeg103 dataset for food segmentation, with deployment and interactive inference via Gradio.

Code release for "Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking"

This repository provides a tutorial and code for reproducing the data and results presented in the following publication: Automated Mapping of Post-Storm Roof Damage Using Deep Learning and Aerial Imagery: A Case Study in the Caribbean (Kucharczyk, Nesbit, & Hugenholtz, 2025, Remote Sensing).

This repository contains the example of fine-tuning panoptic segmentation model.

Assistive robot teleoperation system for blind and visually impaired users using ROS 2, haptic feedback (PS5 DualSense), shared autonomy, and real-time computer vision.

Open source project for waste detection developed by students of postgraduate course Artificial Intelligence with Deep Learning UPC

SimpleGVI: A fast and easy-to-use tool for Green View Index (GVI) calculation based on Mask2Former.

A unified, feed-forward model integrating the MapAnything 3D reconstruction backbone with Mask2Former for multi-view consistent panoptic segmentation. This approach provides feature-rich and metric accurate semantic maps for indoor robot navigation while eliminating the need for posed inputs and costly test-time optimization.

Detectron2 Object Detection, Instance Segmentation, Keypoints Detection, Panoptic Segmentation in PyTorch Fine-tuning.

Hugging Face Object Detection, Instance Segmentation, Semantic Segmentation, Panoptic Segmentation in PyTorch Fine-tuning.

[ICME 2026] The official Dataset and PyTorch implementation of Occlusion-Aware Panoptic Segmentation with Joint Position Embedding and Occlusion-Level Attention

BEACON improves transparent object instance segmentation with boundary supervision and content-adaptive query initialization on top of Mask2Former.

Official repo for "Instance Segmentation in Autonomous Log Grasping Using EfficientViT-SAM MP-Former" paper