OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs
This work addresses the challenge of improving 3D-awareness in GANs for computer vision applications, representing an incremental advancement in representation methods.
The paper tackles the problem of generating realistic and view-consistent 3D images from 2D collections by introducing OrthoPlanes, a hybrid explicit-implicit representation, achieving state-of-the-art results on FFHQ and SHHQ datasets.
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/}.