GIFT bootstraps image-to-CAD generation by turning inference-time failures into synthetic training data, reducing inference compute by 80%.
March 31, 2026
Original Paper
GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback
arXiv · 2603.27448
The Takeaway
The framework uses geometric feedback (IoU) to filter and augment the model's own predictions, effectively amortizing search-time compute into the model weights. This addresses the critical data scarcity bottleneck in high-fidelity engineering and CAD program synthesis.
From the abstract
Generating executable CAD programs from images requires alignment between visual geometry and symbolic program representations, a capability that current methods fail to learn reliably as design complexity increases. Existing fine-tuning approaches rely on either limited supervised datasets or expensive post-training pipelines, resulting in brittle systems that restrict progress in generative CAD design. We argue that the primary bottleneck lies not in model or algorithmic capacity, but in the s