awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectServer MCPDespreCum realizăm clasamentulPresă
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
ChaoningZhang avatar

ChaoningZhang/MobileSAM

0
View on GitHub↗
5,795 stele·585 fork-uri·Jupyter Notebook·Apache-2.0·15 vizualizări

MobileSAM

MobileSAM este un segmentator de imagini ușor și un model de viziune promptabil, conceput pentru izolarea rapidă a obiectelor pe hardware cu resurse limitate. Funcționează ca un instrument automat de mascare a imaginilor, capabil să detecteze și să izoleze obiecte distincte dintr-o întreagă imagine fără input manual.

Sistemul permite mascarea obiectelor bazată pe prompt-uri, folosind puncte de coordonate sau bounding boxes pentru a genera măști precise. De asemenea, suportă segmentarea imaginilor cu toate obiectele prin eșantionarea prompt-urilor conștiente de obiecte pentru a identifica fiecare obiect distinct dintr-o scenă.

Pentru a facilita implementarea pe dispozitive mobile și edge, modelul este compatibil cu exportul ONNX, permițând modelului de viziune să ruleze pe diverse runtime-uri hardware cross-platform.

Features

  • Mobile-Optimized Segmentations - Provides a lightweight image segmenter designed specifically for fast object isolation on mobile hardware.
  • Image Segmentation - Performs all-object image segmentation to isolate every distinct object across a scene.
  • Object Mask Generators - Creates precise object outlines using point or box prompts as input.
  • Point-Based Mask Generators - Generates precise segmentation masks using coordinate points and bounding box prompts.
  • Automatic Prompt Generators - Generates a grid of candidate prompts to automatically identify and mask all objects in an image.
  • SAM-Based Implementations - Implements a mobile-optimized version of the Segment Anything Model architecture.
  • Prompt-Based Segmentations - Implements prompt-based segmentation using bounding boxes or points to identify specific image areas.
  • Promptable Segmentation Tools - Provides a model that generates masks based on multi-modal prompts such as points and boxes.
  • AI Image Masking - Functions as an automatic masking tool to isolate distinct objects using neural networks.
  • Image Encoders - Implements a decoupled image encoder to extract spatial features for fast mask decoding.
  • Knowledge Distillation - Uses knowledge distillation to compress a large teacher model into a lightweight student model.
  • ONNX Model Exporters - Provides tools to export the vision model into the standardized ONNX format for edge deployment.
  • Vision Transformers - Employs a lightweight vision transformer with reduced attention heads and layers for efficiency.
  • Image segmentation - Listed in the “Image segmentation” section of the Ailia Models awesome list.

Istoric stele

Graficul istoricului de stele pentru chaoningzhang/mobilesamGraficul istoricului de stele pentru chaoningzhang/mobilesam

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Întrebări frecvente

Ce face chaoningzhang/mobilesam?

MobileSAM este un segmentator de imagini ușor și un model de viziune promptabil, conceput pentru izolarea rapidă a obiectelor pe hardware cu resurse limitate. Funcționează ca un instrument automat de mascare a imaginilor, capabil să detecteze și să izoleze obiecte distincte dintr-o întreagă imagine fără input manual.

Care sunt principalele funcționalități ale chaoningzhang/mobilesam?

Principalele funcționalități ale chaoningzhang/mobilesam sunt: Mobile-Optimized Segmentations, Image Segmentation, Object Mask Generators, Point-Based Mask Generators, Automatic Prompt Generators, SAM-Based Implementations, Prompt-Based Segmentations, Promptable Segmentation Tools.

Care sunt câteva alternative open-source pentru chaoningzhang/mobilesam?

Alternativele open-source pentru chaoningzhang/mobilesam includ: casia-lmc-lab/fastsam — FastSAM is an image segmentation framework that uses convolutional neural networks to isolate visual elements and… facebookresearch/segment-anything — This project provides a deep learning architecture designed to identify and isolate distinct objects within images by… paddlepaddle/paddledetection — PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of… ant-research/magicquill — MagicQuill is a suite of interactive tools for image segmentation, diffusion-based editing, layered composition, and… datawhalechina/thorough-pytorch — This project is an educational resource and comprehensive guide for implementing and deploying deep learning models… microsoft/swin-transformer — Swin-Transformer is a deep learning framework designed for training and deploying hierarchical vision transformer…

Alternative open-source pentru MobileSAM

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu MobileSAM.
  • casia-lmc-lab/fastsamAvatar CASIA-LMC-Lab

    CASIA-LMC-Lab/FastSAM

    8,364Vezi pe GitHub↗

    FastSAM is an image segmentation framework that uses convolutional neural networks to isolate visual elements and generate masks for detectable objects within images. It provides a system for both automatic all-object segmentation and promptable image segmentation. The project utilizes an inference-optimized architecture to reduce computational overhead, enabling faster mask generation and real-time visual analysis. It supports the creation of precise masks through various prompt inputs, including points, bounding boxes, and text descriptions. The framework covers broader computer vision cap

    Python
    Vezi pe GitHub↗8,364
  • facebookresearch/segment-anythingAvatar facebookresearch

    facebookresearch/segment-anything

    54,353Vezi pe GitHub↗

    This project provides a deep learning architecture designed to identify and isolate distinct objects within images by generating precise pixel-level masks. It functions as a browser-based inference engine, enabling the execution of complex machine learning models directly within web environments without requiring server-side processing. The system distinguishes itself by utilizing hardware-accelerated execution and parallel processing to achieve real-time segmentation speeds. It supports prompt-based mask decoding, allowing users to generate spatial masks by providing specific points or boxes

    Jupyter Notebook
    Vezi pe GitHub↗54,353
  • paddlepaddle/paddledetectionAvatar PaddlePaddle

    PaddlePaddle/PaddleDetection

    14,243Vezi pe GitHub↗

    PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

    Pythonblazefacedeepsortdetr
    Vezi pe GitHub↗14,243
  • ant-research/magicquillAvatar ant-research

    ant-research/MagicQuill

    3,682Vezi pe GitHub↗

    MagicQuill is a suite of interactive tools for image segmentation, diffusion-based editing, layered composition, and prompt-guided visual synthesis. It functions as a diffusion model image editor and a layered visual composition tool, enabling the addition, removal, and recoloring of image elements through a combination of sketches and text prompts. The system features a prompt-guided image generator that predicts editing instructions by analyzing user drawings to automatically populate text prompts. It allows for visual style control by swapping generative model weights to shift outputs betw

    Pythonaigcgradioimage-editing
    Vezi pe GitHub↗3,682
  • Vezi toate cele 30 alternative pentru MobileSAM→