davidcastagnetoa/skills

esrgan_super_resolution

Super-resolución de la foto del documento para mejorar calidad del face match cuando la foto es de baja resolución

First seen Mar 2, 2026

Installation

$ npx skills add davidcastagnetoa/skills --skill esrgan_super_resolution

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from davidcastagnetoa/skills · top by installs.

npx skills add davidcastagnetoa/skills

Browse all from davidcastagnetoa/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 1
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,316 B
  • docs SUMMARY.md 147 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 14 installs

SKILL.md

esrgansuperresolution

ESRGAN (Enhanced Super-Resolution GAN) aumenta la resolución de la foto del documento ×4, mejorando significativamente la calidad del face match en documentos con fotos de baja resolución o antiguas.

When to use

Aplicar cuando la foto extraída del documento tenga resolución menor a 100×100 píxeles o calidad BRISQUE > 50.

Instructions

  1. Instalar Real-ESRGAN: pip install realesrgan.
  2. Descargar modelo: RealESRGAN_x4plus.pthhttps://github.com/xinntao/Real-ESRGAN.
  3. Inicializar: upsampler = RealESRGANer(scale=4, modelpath='RealESRGANx4plus.pth', tile=0, tilepad=10, prepad=0, half=True).
  4. Aplicar: output, = upsampler.enhance(facecrop, outscale=4).
  5. Redimensionar resultado al tamaño esperado por ArcFace (112×112).
  6. Usar solo cuando sea necesario para no añadir latencia innecesaria.

Notes

  • Repositorio: https://github.com/xinntao/Real-ESRGAN
  • half=True usa FP16 en GPU, reduciendo memoria y aumentando velocidad.
  • Benchmark: mejora el face match score ~0.05-0.15 en fotos de documentos de baja calidad.