# HypoX64/DeepMosaics

Automatically remove the mosaics in images and videos, or add mosaics to them.

Repository: https://github.com/HypoX64/DeepMosaics
Canonical: https://ross.abutalabs.com/products/deepmosaics
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: pytorch, deep-learning, computer-vision, mosaic, video-inpainting
Last push: 2024-08-30T23:56:47+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2738, "days_push": 733, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2633, forks 484 (observed 2026-08-28T04:07:06.173001+00:00)

## What it is
DeepMosaics is a Python application that automatically removes or adds mosaics in images and videos using semantic segmentation and image-to-image translation models. It also supports style transfer and ships with a Windows GUI binary plus a web demo.

## Use cases
- remove mosaic from a video
- automatically blur faces in images
- clean censored mosaics from photos
- add mosaic to sensitive regions automatically
- apply style transfer to images
- inpaint mosaic-covered regions in videos

## When to choose
- you need automated mosaic detection and removal on images or videos
- you want a prebuilt GUI or web demo without writing code
- you need GPU-accelerated PyTorch-based image-to-image processing

## When to avoid
- you need high-fidelity restoration of heavily censored content - results are approximate
- you need a production video-editing pipeline rather than a research tool
- you require non-GPL licensing for redistribution

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, video-processing, machine-learning, deep-learning, computer-vision
- domain: computer-vision, image-processing, deep-learning
- platform: windows, python
- tags: mosaic-removal, video-inpainting, semantic-segmentation, image-to-image-translation, style-transfer, pytorch, gui, video, linux, macos, gpu

## Member repositories
- HypoX64/DeepMosaics (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.173001+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 2026-08-30T02:19:34.745963+00:00, confidence not recorded.
  - readme: https://github.com/HypoX64/DeepMosaics (fetched 2026-08-28T04:07:06.173001+00:00, sha 612cd8e0d431)
- Data as of 2026-08-30T08:39:29.467469+00:00.