Skip to content
Back to skills

Geometry Rendering

ASecurity

"Reconstruct 3DMM vertices, serialize mesh outputs, and manage

  • 247 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 8, 2026
content-marketingc++api

Works with

  • cli
  • api

Security analysis

A100/100

Pro scans all 8 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill geometry-rendering --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Geometry Rendering?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Geometry Rendering
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-geometry-rendering/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-geometry-rendering)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: geometry-rendering
description: "Reconstruct 3DMM vertices, serialize mesh outputs, and manage
  3DDFA rendering helpers."
disable-model-invocation: true
metadata:
  disco-role: operating
license: MIT
---

# geometry-rendering

Use this sub-skill for the geometry side of 3DDFA: parameter reconstruction, ROI-to-image conversion, sparse and dense vertices, mesh serialization, pose matrices, depth/PNCC/PAF outputs, and the Cython-backed render path.

## Use when
- you have a 62-D parameter vector or cropped ROI and need 68 landmarks or dense vertices;
- you need PLY, OBJ, `.mat`, depth, PNCC, PAF, or pose artifacts;
- you need to build or troubleshoot `utils.cython`;
- you need dense render or video assembly helpers.

## Start here
- [API reference](references/api-reference.md)
- [Output formats](references/output-formats.md)
- [Rendering and Cython](references/rendering-and-cython.md)
- [Data artifacts](references/data-artifacts.md)
- [Troubleshooting](references/troubleshooting.md)

## Bundled helpers
- [scripts/smoke_geometry.py](scripts/smoke_geometry.py)
- [scripts/images_to_video.py](scripts/images_to_video.py)

## Route elsewhere
- Full detector/model inference and CLI flags belong in the sibling inference sub-skill.
- Training losses, benchmark scripts, and dataset preparation belong in the training sub-skill.
- ONNX export and the C++ port belong in the C++ sub-skill.

## Working facts
- `utils.ddfa.reconstruct_vertex` is the canonical 3DMM reconstruction entry point.
- The verified smoke for a zero 62-D vector returns sparse `(3, 68)` and dense `(3, 53215)` vertices.
- `visualize/tri.mat` provides the triangle indices used by the renderer paths.
- `utils.render` and `utils.lighting` depend on the compiled `mesh_core_cython` extension.

Files in this skill

  • SKILL.md1.7 KB
  • references/api-reference.md4.6 KB
  • references/data-artifacts.md2.1 KB
  • references/output-formats.md2.5 KB
  • references/rendering-and-cython.md2.2 KB
  • references/troubleshooting.md2.4 KB
  • scripts/images_to_video.py2.4 KB
  • scripts/smoke_geometry.py1.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.