# SysCV/sam-hq

Segment Anything in High Quality [NeurIPS 2023]

Repository: https://github.com/SysCV/sam-hq
Canonical: https://ross.abutalabs.com/products/sam-hq
Homepage: https://arxiv.org/abs/2306.01567
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: sam, segmentation, segment-anything, zero-shot-segmentation, high-quality, segment-anything-model
Last push: 2025-09-12T00:00:27+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 35, longevity 85
- inputs: {"age_days": 1190, "days_push": 356, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4255, forks 264 (observed 2026-08-28T04:08:40.499420+00:00)

## What it is
HQ-SAM (Segment Anything in High Quality) upgrades Meta's Segment Anything Model with a learnable High-Quality Output Token for accurate zero-shot segmentation of objects with intricate structures. It provides pretrained checkpoints, a Python package, and integrations with Hugging Face Transformers, OpenMMLab, and annotation tools.

## Use cases
- segment objects in images with high-quality masks
- zero-shot image segmentation without task-specific training
- generate fine-grained mask annotations for datasets
- segment geospatial or satellite imagery
- promptable segmentation with points or boxes
- video object segmentation pipelines

## When to choose
- you need higher mask quality than vanilla SAM, especially for intricate object boundaries
- you want zero-shot promptable segmentation with pretrained checkpoints
- you need fine-grained masks for annotation or downstream multimodal models

## When to avoid
- you need real-time segmentation on CPU-constrained hardware
- you only need classification or detection rather than pixel-level masks
- you want a fully trained task-specific segmentation model

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: segment-anything, sam, image-segmentation, zero-shot, hq-sam, mask-prediction, promptable-segmentation, neurips-2023, gpu

## Member repositories
- SysCV/sam-hq (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:40.499420+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:08.423948+00:00, confidence not recorded.
  - readme: https://github.com/SysCV/sam-hq (fetched 2026-08-28T04:08:40.499420+00:00, sha f55599345618)
  - homepage: https://arxiv.org/abs/2306.01567 (fetched 2026-08-29T09:11:51.213340+00:00, sha be00cadbb832)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T09:11:51.220254+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T09:11:51.217210+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T09:11:51.222190+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T09:11:51.218782+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.