Object pop-up: Can we infer 3D objects and their poses from human interactions alone?
We propose a novel characterization of the mold algorithm to work on arbitrary curved surfaces.
We propose a novel characterization of the mold algorithm to work on arbitrary curved surfaces.
We propose a parallel decoding algorithm to speedup transformer inference for translation.
A novel approach for non-rigid correspondence based on mesh-free methods.
We combine the spectra of different linear operators to learn of to semantically modify shape geometries.
We propose a novel characterization of the mold algorithm to work on arbitrary curved surfaces.
A data-driven solution and analysis of the theoretical problem of recovering a shape from its spectrum
We propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds.
Inspired by the Functional Maps paradigma, we learn a linearly-invariant embedding for 3D Shape Matching
A full automatic pipeline for 3D human shapes that combine intrinsic shape matching and template registration