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 3d-wireframe-reconstruction
No benchmarks available.
Use these libraries to find 3d-wireframe-reconstruction models and implementations
No datasets available.
No subtasks available.
The proposed NEAT enjoys the joint optimization of the neural fields and the global junctions from scratch, using view-dependent 2D observations without precomputed cross-view feature matching, demonstrating its superiority over state-of-the-art alternatives for 3D wireframe reconstruction.
This work introduces PC2WF, the first end-to-end trainable deep network architecture to convert a 3D point cloud into a wireframe model, and produces wireframe abstractions of good quality and outperforms several baselines.
Adding a benchmark result helps the community track progress.