Dr.3D: Adapting 3D GANs to Artistic Drawings
This work addresses a domain-specific problem for computer graphics and AI art by adapting existing 3D GANs to artistic drawings, representing an incremental advancement.
The paper tackles the challenge of extending 3D GANs to artistic portrait drawings by proposing Dr.3D, an adaptation approach that handles geometric ambiguity, enabling multi-view consistent semantic editing of drawings.
While 3D GANs have recently demonstrated the high-quality synthesis of multi-view consistent images and 3D shapes, they are mainly restricted to photo-realistic human portraits. This paper aims to extend 3D GANs to a different, but meaningful visual form: artistic portrait drawings. However, extending existing 3D GANs to drawings is challenging due to the inevitable geometric ambiguity present in drawings. To tackle this, we present Dr.3D, a novel adaptation approach that adapts an existing 3D GAN to artistic drawings. Dr.3D is equipped with three novel components to handle the geometric ambiguity: a deformation-aware 3D synthesis network, an alternating adaptation of pose estimation and image synthesis, and geometric priors. Experiments show that our approach can successfully adapt 3D GANs to drawings and enable multi-view consistent semantic editing of drawings.