Learning Generative Models of Textured 3D Meshes from Real-World Images

Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle pose and appearance, enable downstream applications in computer graphics, and improve the ability of generative models to...

Full description

Saved in:
Bibliographic Details
Main Authors: Pavllo, Dario, Kohler, Jonas, Hofmann, Thomas, Lucchi, Aurelien
Format: Conference Proceeding
Language:English
Subjects:
3D from a single image and shape-from-x
Annotations
Codes
Computational modeling
Computer vision
Image and video synthesis
Neural generative models
Semantics
Solid modeling
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle pose and appearance, enable downstream applications in computer graphics, and improve the ability of generative models to understand the concept of image formation. Although there has been prior work on learning such models from collections of 2D images, these approaches require a delicate pose estimation step that exploits annotated keypoints, thereby restricting their applicability to a few specific datasets. In this work, we propose a GAN framework for generating textured triangle meshes without relying on such annotations. We show that the performance of our approach is on par with prior work that relies on ground-truth keypoints, and more importantly, we demonstrate the generality of our method by setting new baselines on a larger set of categories from ImageNet-for which keypoints are not available-without any class-specific hyperparameter tuning. We release our code at https://github.com/dariopavllo/textured-3d-gan
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.01362