Authors:
Pragati Jaiswal
1
;
2
;
Tewodros Amberbir Habtegebrial
1
;
2
and
Didier Stricker
2
;
1
Affiliations:
1
RPTU, Technische Universität Kaiserslautern, Germany
;
2
DFKI, German Research Center for Artificial Intelligence, Germany
Keyword(s):
Single-View Reconstruction, 3D Face Reconstruction, 1D-Diffusion.
Abstract:
In the field of 3D reconstruction, recent developments, especially in face reconstruction, have shown considerable promise. Despite these achievements, many of these techniques depend heavily on a large number of input views and are inefficient limiting their practicality. This paper proposes a solution to these challenges by focusing on single-view, full 3D head reconstruction. Our approach leverages a 1D diffusion model in combination with RGB image features and a neural parametric latent representation. Specifically, we train a system to learn latent codes conditioned on features extracted from a single input image. The model directly processes the input image at inference to generate latent codes, which are then decoded into a 3D mesh. Our method achieves high-fidelity reconstructions that outperform state-of-the-art approaches such as 3D Morphable Models, Neural Parametric Head Models, and existing methods for head reconstruction.