GAN-powered model- & landmark-free reconstruction: a versatile approach for high-quality 3D facial and object recovery from single images
- In recent years, 3D facial reconstructions from single images have garnered significant interest. Most of the approaches are based on 3D Morphable Model (3DMM) fitting to reconstruct the 3D face shape. Concurrently, the adoption of Generative Adversarial Networks (GAN) has been gaining momentum to improve the texture of reconstructed faces. In this paper, we propose a fundamentally different approach to reconstructing the 3D head shape from a single image by harnessing the power of GAN. Our method predicts three maps of normal vectors of the head’s frontal, left, and right poses. We are thus presenting a model-free method that does not require any prior knowledge of the object’s geometry to be reconstructed. The key advantage of our proposed approach is the substantial improvement in reconstruction quality compared to existing methods, particularly in the case of facial regions that are self-occluded in the input image. Our method is not limited to 3d face reconstruction. It is generic and applicable to multiple kinds of 3D objects. To illustrate the versatility of our method, we demonstrate its efficacy in reconstructing the entire human body. By delivering a model-free method capable of generating high-quality 3D reconstructions, this paper not only advances the field of 3D facial reconstruction but also provides a foundation for future research and applications spanning multiple object types. The implications of this work have the potential to extend far beyond facial reconstruction, paving the way for innovative solutions and discoveries in various domains.
Author of HS Reutlingen | Danner, Michael; Rätsch, Matthias |
---|---|
DOI: | https://doi.org/10.1007/978-3-031-39059-3_27 |
ISBN: | 978-3-031-39058-6 |
ISBN: | 978-3-031-39059-3 |
Erschienen in: | Deep Learning Theory and Applications : 4th International Conference, DeLTA 2023, Rome, Italy, 13-14 July 2023, proceedings |
Publisher: | Springer |
Place of publication: | Cham |
Document Type: | Conference proceeding |
Language: | English |
Publication year: | 2023 |
Page Number: | 16 |
First Page: | 403 |
Last Page: | 418 |
PPN: | Im Katalog der Hochschule Reutlingen ansehen |
DDC classes: | 004 Informatik |
Open access?: | Nein |
Licence (German): | In Copyright - Urheberrechtlich geschützt |