Can I visualize the differences between two models?

Yes, unless the --no-export flag is used, the tool generates GLB files highlighting common geometry, missing parts, and extra geometry for easy visual inspection.

How do I integrate this into an automated pipeline?

You can use the --json flag to receive structured data and the --no-export flag to skip visualization, making it easy to parse results in shell scripts or Python loops.

Which 3D file formats are supported for comparison?

The skill supports STEP (.step, .stp) and BREP for high-fidelity CAD data, as well as STL files for mesh-based comparisons.

What metrics does the tool provide for ML evaluation?

It provides Intersection over Union (IoU), Dice coefficient (F1 score), Precision, and Recall, as well as diagnostic metrics like volume ratio and center offset.

CAD Model Compare

Name: CAD Model Compare
Author: rawwerks

byrawwerks

•

デザインツール

Evaluates 3D CAD models against reference designs using boolean operations and geometric similarity metrics.

概要

This skill provides a robust framework for comparing 3D models within the Claude Code environment, utilizing OpenCASCADE to perform precise boolean operations. It calculates industry-standard metrics such as Intersection over Union (IoU), Dice coefficients, and precision/recall scores to quantify the accuracy of generated geometry against gold references. Ideal for developers working on 3D generative AI or automated CAD validation, it generates detailed reports and GLB visualizations to identify specific areas of over-generation, under-generation, or positional offsets.

主な機能

Supports high-fidelity CAD formats including STEP, BREP, and STL meshes.
Calculates standard similarity metrics including IoU, Dice, Precision, and Recall for 3D volumes.
Provides automated diagnostic interpretation of size, position, and volume discrepancies.
1 GitHub stars
Generates GLB visualization files to isolate missing, extra, and common geometry.
Includes a JSON-only output mode for seamless integration into ML training and evaluation pipelines.

ユースケース

Evaluating the performance of AI-generated 3D models against ground-truth reference designs.
Comparing revisions of mechanical CAD parts to track geometric changes and volume shifts.
Implementing automated quality gates in 3D design workflows using standardized similarity metrics.

概要

主な機能

Supports high-fidelity CAD formats including STEP, BREP, and STL meshes.
Calculates standard similarity metrics including IoU, Dice, Precision, and Recall for 3D volumes.
Provides automated diagnostic interpretation of size, position, and volume discrepancies.
1 GitHub stars
Generates GLB visualization files to isolate missing, extra, and common geometry.
Includes a JSON-only output mode for seamless integration into ML training and evaluation pipelines.

ユースケース

Evaluating the performance of AI-generated 3D models against ground-truth reference designs.
Comparing revisions of mechanical CAD parts to track geometric changes and volume shifts.
Implementing automated quality gates in 3D design workflows using standardized similarity metrics.