Papers › CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance...

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

27 Feb 2024CVPR 2024 1arXiv:2402.17678archive 2025-07-28

Mohammad Sadil Khan, Elona Dupont, Sk Aziz Ali, Kseniya Cherenkova, Anis Kacem, Djamila Aouada

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D ReconstructionCAD Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
CAD Reconstruction CC3D CAD-SIGNet Chamfer Distance 32.6 #3 of 4 Archive leaderboard report
CAD Reconstruction CC3D CAD-SIGNet Chamfer Distance (median) 4.42 #3 of 4 Archive leaderboard report
CAD Reconstruction CC3D CAD-SIGNet Invalid Ratio 15.5 #3 of 4 Archive leaderboard report
CAD Reconstruction CC3D CAD-SIGNet IoU 39.1 #3 of 4 Archive leaderboard report
CAD Reconstruction DeepCAD CAD-SIGNet Camfer Distance (median) 0.29 #3 of 11 Archive leaderboard report
CAD Reconstruction DeepCAD CAD-SIGNet Chamfer Distance 6.81 #3 of 11 Archive leaderboard report
CAD Reconstruction DeepCAD CAD-SIGNet Invalidi Ratio 5.0 #3 of 11 Archive leaderboard report
CAD Reconstruction DeepCAD CAD-SIGNet IoU 77.3 #3 of 11 Archive leaderboard report
CAD Reconstruction Fusion 360 Gallery CAD-SIGNet Chamfer Distance 14.5 #9 of 11 Archive leaderboard report
CAD Reconstruction Fusion 360 Gallery CAD-SIGNet Chamfer Distance (median) 0.70 #9 of 11 Archive leaderboard report
CAD Reconstruction Fusion 360 Gallery CAD-SIGNet Invalid Ratio 9.3 #9 of 11 Archive leaderboard report
CAD Reconstruction Fusion 360 Gallery CAD-SIGNet IoU 58.4 #9 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections