AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation

Jinbo Yang, Shikai Jing, Mingyue Yuan

NeurIPS 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces intent-oriented text-to-CAD generation, where design intent is encoded as recoverable code-level signal so generated CAD programs expose reusable, modifiable structure.

Problem

Text-to-CAD generation typically produces executable geometry, but practical CAD workflows also need generated programs that expose reusable structure supporting later modification.

Approach

Frames text-to-CAD as intent-oriented generation in which design intent is expressed as recoverable code-level signal, using semantic-parametric supervision to shape generated CAD programs.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic lifting to the supervision target (primitive-only to semantic) (ablation)SFT text-to-CadQuery model · IntentCAD-100K testInvalid Ratio (%): 2.39 -> 0.22Improved
add semantic lifting to the supervision target (ablation)SFT text-to-CadQuery model · IntentCAD-100K testMean Chamfer Distance (x10^3): 1.44 -> 0.46Improved
add parametric lifting on top of semantic lifting (ablation)SFT text-to-CadQuery model · IntentCAD-100K testIR, AR, Median CDNo clear effect
add parametric lifting on top of semantic lifting (ablation)SFT text-to-CadQuery model · IntentCAD-100K testMean Chamfer Distance (x10^3): 0.46 -> 0.57No clear effect
add semantic lifting to the supervision target (ablation)zero-shot editing · IntentCAD-Edit-1KEdit Success Rate (%): 41.80 -> 88.90Improved
add parametric lifting on top of semantic lifting (ablation)zero-shot editing · IntentCAD-Edit-1KCE@ES (%): 91.00 -> 95.82Improved
add parametric lifting on top of semantic lifting (ablation)zero-shot editing · IntentCAD-Edit-1KFE@ES (%): 95.17 -> 92.51Mixed
add semantic lifting to the supervision target (ablation)visually grounded editing · Visually grounded editing (200 cases)Edit Success (%): 36.50 -> 66.00Improved
add parametric lifting on top of semantic lifting (ablation)visually grounded editing · Visually grounded editing (200 cases)Edit Success (%): 66.00 -> 78.50Improved
add parametric lifting for feature edits in visually grounded editing (ablation)visually grounded editing · Visually grounded editing (200 cases)FE@ES (%): 86.25 -> 78.75Hurt
fine-tune open backbone on IntentCAD SFTQwen3.5-9B · IntentCAD-100KInvalid Ratio (%): 99.86 -> 0.20Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy