# HugoTini/DeepBump

Normal & height maps generation from single pictures

Repository: https://github.com/HugoTini/DeepBump
Canonical: https://ross.abutalabs.com/products/deepbump
Homepage: https://hugotini.github.io/deepbump
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: normalmap, blender-addon, blender, generator, ml, machine-learning, heightmap
Last push: 2025-03-17T14:37:47+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 11, release rhythm 8, longevity 100
- inputs: {"age_days": 2300, "days_push": 534, "days_rel": 534, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1399, forks 61 (observed 2026-08-28T04:04:36.934357+00:00)

## What it is
DeepBump is a machine-learning tool that generates normal, height, and curvature maps from single pictures, using a U-Net (MobileNetV2) model. It ships as a Blender add-on and a command-line program.

## Use cases
- generate normal maps from photos
- convert albedo textures to normal maps
- generate height maps from normal maps
- generate curvature maps from normal maps
- upscale low-res textures
- batch generate texture maps from the command line

## When to choose
- you work in Blender and need quick normal/height maps from photos
- you want ML-based texture map generation instead of grayscale-slope approximations
- you need a CLI for batch texture map generation

## When to avoid
- you need a standalone GUI application outside Blender
- you need to retrain the model (training code is not available)
- you need other PBR maps like roughness or metallic

## Facets
- artifact type: plugin
- maturity: active
- function: machine-learning, image-processing, cli
- domain: graphics, machine-learning
- platform: python, cross-platform, cli
- tags: normal-map, height-map, blender-addon, texture-generation, onnx, pbr-texturing, game-development, blender

## Member repositories
- HugoTini/DeepBump (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:36.934357+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 2026-08-30T04:39:08.758791+00:00, confidence not recorded.
  - readme: https://github.com/HugoTini/DeepBump (fetched 2026-08-28T04:04:36.934357+00:00, sha 02eaea0b69be)
  - homepage: https://hugotini.github.io/deepbump (fetched 2026-08-29T11:53:23.988446+00:00, sha 2db6eb3a5fd6)
- Data as of 2026-08-30T08:39:29.467469+00:00.