Search Results for author:
Found 3 papers, 1 papers with code
Dynamic Plane Convolutional Occupancy Networks
To further exploit translational equivariance, convolutional neural networks are applied to process the plane features.
Ranked #2 on
3D Reconstruction
on ShapeNet
Barcodes as summary of objective function's topology
We apply the canonical forms (barcodes) of gradient Morse complexes to explore topology of loss surfaces.
Barcodes as summary of objective functions' topology
We apply canonical forms of gradient complexes (barcodes) to explore neural networks loss surfaces.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
