CADENA: Stepwise CAD Reverse Engineering

Hugging Face Daily Papers Papers
cad reverse-engineering parametric-modeling benchmark

Summary

Introduces CADENA, a model that reconstructs 3D meshes as parametric CAD programs step by step, comparing intermediate geometry with the target, plus the CADENA-Bench benchmark. Outperforms prior methods on multiple datasets.

Computer-Aided Design (CAD) underpins modern engineering, yet converting existing shapes into editable models still demands substantial expert effort. Most AI systems emit the entire CAD program in a single pass, never inspecting the intermediate geometry. In contrast, human engineers build a part feature by feature, checking after each operation what remains to be modeled. We introduce CADENA (Spanish for "chain"), a model that reconstructs a 3D mesh as a parametric CAD program, growing its sequence of operations one at a time and comparing the target with the currently predicted geometry at every step. We also address the lack of benchmarks for evaluating reverse-engineering methods on mechanical parts, introducing CADENA-Bench, a benchmark that measures performance across categories of mechanical parts. CADENA outperforms prior methods on CADENA-Bench and on the DeepCAD, Fusion 360, and MCB datasets. Code is available at https://github.com/zhemdi/cadena, model weights at https://huggingface.co/kulibinai/cadena, and CADENA-Bench at https://huggingface.co/datasets/kulibinai/cadena-bench.
Original Article
View Cached Full Text

Cached at: 08/04/26, 05:37 AM

Paper page - CADENA: Stepwise CAD Reverse Engineering

Source: https://huggingface.co/papers/2608.00799 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

Computer-AidedDesign(CAD)underpinsmodernengineering,yetconvertingexistingshapesintoeditablemodelsstilldemandssubstantialexperteffort.MostAIsystemsemittheentireCADprograminasinglepass,neverinspectingtheintermediategeometry.Incontrast,humanengineersbuildapartfeaturebyfeature,checkingaftereachoperationwhatremainstobemodeled.WeintroduceCADENA(Spanishfor“chain“),amodelthatreconstructsa3DmeshasaparametricCADprogram,growingitssequenceofoperationsoneatatimeandcomparingthetargetwiththecurrentlypredictedgeometryateverystep.Wealsoaddressthelackofbenchmarksforevaluatingreverse-engineeringmethodsonmechanicalparts,introducingCADENA-Bench,abenchmarkthatmeasuresperformanceacrosscategoriesofmechanicalparts.CADENAoutperformspriormethodsonCADENA-BenchandontheDeepCAD,Fusion360,andMCBdatasets.Codeisavailableathttps://github.com/zhemdi/cadena,modelweightsathttps://huggingface.co/kulibinai/cadena,andCADENA-Benchathttps://huggingface.co/datasets/kulibinai/cadena-bench.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2608\.00799

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### kulibinai/cadena Image-to-Text• Updated38 minutes ago • 1

Datasets citing this paper1

#### kulibinai/cadena-bench Viewer• Updated38 minutes ago • 3.4k • 23 • 1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.00799 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

GenCAD

Hacker News Top

GenCAD introduces an image-conditional model that generates full parametric CAD command histories using transformers and diffusion priors, enabling precise and modifiable 3D modeling from images.

Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback

Hugging Face Daily Papers

This paper introduces a new task formulation for CAD generation that incorporates finite element analysis as feedback, along with improved supervision signals like a text-only blueprint schema and multi-view image renderer, leading to better geometric reconstruction on benchmarks.

Memory-Augmented Reinforcement Learning Agent for CAD Generation

arXiv cs.AI

This paper proposes a memory-augmented reinforcement learning framework for CAD generation agents that integrates geometric kernel toolchains, dual-track memory, and dynamic utility retrieval to handle complex CAD models with long operation sequences and geometric constraints, achieving improved success rate and geometric consistency.