Command Palette
Search for a command to run...
Cad Reconstruction On Deepcad
Metrics
Camfer Distance (median)
IoU
Results
Performance results of various models on this benchmark
| Paper Title | Repository | |||
|---|---|---|---|---|
| DeepCAD | 9.64 | 46.7 | DeepCAD: A Deep Generative Network for Computer-Aided Design Models | |
| HNC-CAD | 8.64 | 65.3 | Hierarchical Neural Coding for Controllable CAD Model Generation | |
| TransCAD | 4.51 | 65.5 | TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds | - |
| PrismCAD | 4.28 | 72.1 | Reconstructing editable prismatic CAD from rounded voxel models | - |
| Point2Cyl | 4.27 | 73.8 | Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders | - |
| SECAD-Net | 3.65 | 72.9 | SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations | |
| ExtrudeNet | 3.37 | 40.3 | ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing | |
| CAD-Diffuser | 3.02 | 74.3 | Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion. | - |
| CAD-SIGNet | 0.283 | 77.6 | CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention | - |
| CAD-Recode | 0.157 | 92.0 | CAD-Recode: Reverse Engineering CAD Code from Point Clouds |
0 of 10 row(s) selected.