3 papers
cs.CV2022
Building 3D Generative Models from Minimal Data
Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum
We propose a method for constructing generative models of 3D objects from a single 3D mesh and improving them through unsupervised low-shot learning from 2D images. Our method prod…
cs.CV2021
Identity-Expression Ambiguity in 3D Morphable Face Models
Bernhard Egger, Skylar Sutherland, Safa C. Medin +1
3D Morphable Models are a class of generative models commonly used to model faces. They are typically applied to ill-posed problems such as 3D reconstruction from 2D data. Several…
cs.CV2020
Building 3D Morphable Models from a Single Scan
Skylar Sutherland, Bernhard Egger, Joshua Tenenbaum
We propose a method for constructing generative models of 3D objects from a single 3D mesh. Our method produces a 3D morphable model that represents shape and albedo in terms of Ga…