CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention

arXiv:2402.17678v1 Announce Type: new
Abstract: Reverse engineering in the realm of Computer-Aided Design (CAD) has been a longstanding aspiration, though not yet entirely realized. Its primary aim is to uncover the CAD process behind a physical object given its 3D scan. We propose CAD-SIGNet, an end-to-end trainable and auto-regressive architecture to recover the design history of a CAD model represented as a sequence of sketch-and-extrusion from an input point cloud. Our model learns visual-language representations by layer-wise cross-attention between point …

abstract aim arxiv attention cad computer cs.cv design engineering inference instance language layer process type wise