GenCAD

Original Article ↗ Hacker News Discussion ↗

GenCAD is a research project that converts 2D CAD-style images into parametric CAD command sequences, aiming to reconstruct not just 3D geometry but the underlying feature history. Commenters see promise in this representation for search, model generation, and integrating with LLMs, but note that the current system is limited to very simple, noise-free, isometric inputs and a narrow set of operations (mostly extrudes). Many question its practical utility today, arguing that real-world CAD complexity lies in constraints, dimensions, tolerances, and robust geometry kernels—areas where open tools and AI models still lag far behind professional systems.

What GenCAD Produces

  • Discussion centers on the claim that GenCAD “converts CAD latents into parametric CAD commands” and “generates the entire CAD program.”
  • Output is clarified as DeepCAD-style JSON: a sequence of sketch/extrude (pad) operations derived from Onshape data, i.e., a feature history, not a mesh.
  • This history is conceptually CAD-agnostic but in practice still kernel/application dependent, and does not currently map cleanly into arbitrary CAD tools or editable histories elsewhere.

CAD Technology Context

  • Several comments explain that real CAD behavior depends heavily on the geometry kernel and tolerances, especially for fillets, blends, and barely-intersecting surfaces.
  • Portable formats like STEP typically lose the operation history for this reason.
  • GenCAD is described as operating at a CSG-like abstraction (sketch + extrude), with B-rep used only as a downstream representation.
  • It currently supports only simple 2D sketches (lines/arcs/circles) and extrusions; no revolve, fillet, chamfer, drafts, or complex surface workflows.

Perceived Utility and Limitations

  • Many see the demonstrated examples as extremely basic (often a single extrude) and far from “real” parametric CAD work.
  • Several argue that the hard part of CAD is constraints, dimensions, tolerances, and editability; GenCAD does not yet address these.
  • Some view it as a solution in search of a problem; others say they personally struggle with CAD and would welcome reliable sketch/image → parametric model tools.

Practical Usability and Training Constraints

  • Attempts to run the Docker setup exposed missing dependencies; the containerization is criticized as brittle.
  • A user reports that on non-training images, even simple ones, the model almost never produces correct output.
  • The paper’s own limitations section (paraphrased in the thread) says it is trained mostly on noise-free, isometric CAD renders in a very specific visual style and with a very restricted operation vocabulary, which explains poor generalization.

AI/LLM Integration and Alternatives

  • Multiple commenters discuss combining GenCAD-like models with multimodal LLMs: text → image → CAD, or CAD-as-code workflows.
  • There is extensive mention of using LLMs today with OpenSCAD, CadQuery, Build123d, or custom languages; experiences range from “works great for simple parts” to “painful and brittle.”
  • Other AI‑CAD efforts and open-source kernels are cited, plus a recent survey suggesting the field is moving quickly beyond this work.

Meta and Miscellaneous Points

  • Some emphasize that geometric kernels are intrinsically hard; in comparison, CAM toolpath generation is “just” optimization once good geometry exists.
  • Minor side discussions touch on font licensing, autoplay video on the site, mobile layout issues, and containerization (Docker vs Nix).