Paper published in a book (Scientific congresses, symposiums and conference proceedings)
CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention
Sadil Khan, Mohammad; DUPONT, Elona Marcelle Eugénie; Aziz Ali, Sk et al.
2024In CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention
Peer reviewed
 

Files


Full Text
Khan_CAD-SIGNet_CAD_Language_Inference_from_Point_Clouds_using_Layer-wise_Sketch_CVPR_2024_paper.pdf
Author postprint (8.1 MB)
Request a copy
Annexes
Khan_CAD-SIGNet_CAD_Language_CVPR_2024_supplemental.pdf
(11 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Computer Science - Computer Vision and Pattern Recognition
Abstract :
[en] 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 cloud and CAD language embedding. In particular, a new Sketch instance Guided Attention (SGA) module is proposed in order to reconstruct the fine-grained details of the sketches. Thanks to its auto-regressive nature, CAD-SIGNet not only reconstructs a unique full design history of the corresponding CAD model given an input point cloud but also provides multiple plausible design choices. This allows for an interactive reverse engineering scenario by providing designers with multiple next-step choices along with the design process. Extensive experiments on publicly available CAD datasets showcase the effectiveness of our approach against existing baseline models in two settings, namely, full design history recovery and conditional auto-completion from point clouds.
Disciplines :
Computer science
Author, co-author :
Sadil Khan, Mohammad
DUPONT, Elona Marcelle Eugénie ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Aziz Ali, Sk
CHERENKOVA, Kseniya ;  University of Luxembourg
KACEM, Anis  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
AOUADA, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
External co-authors :
yes
Language :
English
Title :
CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention
Publication date :
2024
Event name :
CVF Conference on Computer Vision and Pattern Recognition
Event date :
Mon Jun 17th through Fri Jun 21st, 2024
Main work title :
CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention
Publisher :
IEEE
Peer reviewed :
Peer reviewed
FnR Project :
BRIDGES2021/IS/16849599/FREE-3D
IF/17052459/CASCADES
Available on ORBilu :
since 18 August 2024

Statistics


Number of views
265 (13 by Unilu)
Number of downloads
66 (3 by Unilu)

Bibliography


Similar publications



Contact ORBilu