# hzwer/ICCV2019-LearningToPaint

ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

Repository: https://github.com/hzwer/ICCV2019-LearningToPaint
Canonical: https://ross.abutalabs.com/products/iccv2019-learningtopaint
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, reinforcement-learning, computer-vision, pytorch, painting
Last push: 2025-05-07T03:16:13+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 20, release rhythm 35, longevity 100
- inputs: {"age_days": 2732, "days_push": 483, "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 2305, forks 311 (observed 2026-08-28T04:06:35.749406+00:00)

## What it is
A PyTorch research implementation of the ICCV 2019 paper 'Learning to Paint With Model-based Deep Reinforcement Learning'. It trains agents that decompose images into a small number of painterly strokes using a neural renderer, without human painting data.

## Use cases
- convert an image into a sequence of brush strokes
- generate a video of a machine painting a picture
- research on model-based deep reinforcement learning for image generation
- train a neural renderer for stroke-based image synthesis
- reproduce ICCV 2019 learning-to-paint experiments

## When to choose
- you want to reproduce or extend the LearningToPaint paper
- you need stroke-based image stylization or painting-process animation
- you study model-based DRL with neural renderers

## When to avoid
- you need a production-ready image editing tool
- you want modern maintained dependencies (it pins PyTorch 1.1.0)
- you need high-fidelity photorealistic image generation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, reinforcement-learning, computer-vision, image-processing
- domain: deep-learning, reinforcement-learning, computer-vision, image-processing, artificial-intelligence
- platform: python
- tags: pytorch, neural-renderer, stroke-painting, research-code, iccv2019, linux, gpu

## Member repositories
- hzwer/ICCV2019-LearningToPaint (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:35.749406+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 2026-08-30T02:39:42.278928+00:00, confidence not recorded.
  - readme: https://github.com/hzwer/ICCV2019-LearningToPaint (fetched 2026-08-28T04:06:35.749406+00:00, sha ef724afac09d)
- Data as of 2026-08-30T08:39:29.467469+00:00.