3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in cad-reconstruction-5
No benchmarks available.
Use these libraries to find cad-reconstruction-5 models and implementations
No datasets available.
No subtasks available.
A standard CAD reconstruction task, together with evaluation metrics, and results from a neurally guided search approach for learning CAD reconstruction from sequential 3D CAD data are outlined.
A novel, end-to-end approach to align CAD models to an 3D scan of a scene, enabling transformation of a noisy, incomplete3D scan to a compact, CAD reconstruction with clean, complete object geometry.
SECADNet is introduced, an end- to-end neural network aimed at reconstructing compact and easy-to-edit CAD models in a self-supervised manner and advocate the use of implicit fields for sketch representation, which allows for creating CAD variations by interpolating latent codes in the sketch latent space.
Adding a benchmark result helps the community track progress.