Search Results for author:
Found 4 papers, 2 papers with code
Pix2Repair: Implicit Shape Restoration from Images
We also introduce Fantastic Breaks Imaged, the first large-scale dataset of 11, 653 real-world images of fractured objects for training and evaluating image-based shape repair approaches.
Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts
Automated shape repair approaches currently lack access to datasets that describe real-world damaged geometry.
DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair
We generate a high-resolution restoration shape by inferring a corresponding complete shape and a break surface from an input fractured shape.
DeepMend: Learning Occupancy Functions to Represent Shape for Repair
We represent the occupancy of a fractured shape as the conjunction of the occupancy of an underlying complete shape and the fracture surface, which we model as functions of latent codes using neural networks.
