OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs

TL;DR

OrthoPlanes introduces a hybrid explicit-implicit 3D representation that enhances GANs' ability to generate realistic, view-consistent images with detailed geometry, outperforming previous methods on challenging datasets.

Contribution

The paper proposes OrthoPlanes, a novel hybrid explicit-implicit 3D representation that improves scalability and expressiveness in GAN-based image synthesis.

Findings

Achieves state-of-the-art results on FFHQ and SHHQ datasets.

Handles challenging view-angles and articulated objects.

Demonstrates superior realism and view consistency.

Abstract

We present a new method for generating realistic and view-consistent images with fine geometry from 2D image collections. Our method proposes a hybrid explicit-implicit representation called \textbf{OrthoPlanes}, which encodes fine-grained 3D information in feature maps that can be efficiently generated by modifying 2D StyleGANs. Compared to previous representations, our method has better scalability and expressiveness with clear and explicit information. As a result, our method can handle more challenging view-angles and synthesize articulated objects with high spatial degree of freedom. Experiments demonstrate that our method achieves state-of-the-art results on FFHQ and SHHQ datasets, both quantitatively and qualitatively. Project page: \url{https://orthoplanes.github.io/}.