Detailed 3D Face Reconstruction from a Single RGB Image

Rotger, Gemma; Moreno-Noguer, Francesc; Lumbreras, Felipe; Agudo, Antonio

doi:10.24132/jwscg.2019.27.2.3

Cited by 4 publications

(2 citation statements)

References 28 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, 3DMMs are constructed from 3D scans which might be hard to obtain for many classes. Other more descriptive and flexible 3D representations include depth maps [29]- [31], regular meshes [32], [33], and volumetric grids [34], although many of these approaches still rely on 3DMM in their intermediate steps.…”

Section: Few-or Single-view Head Reconstructionmentioning

confidence: 99%

Multi-NeuS: 3D Head Portraits From Single Image With Neural Implicit Functions

Burkov,

Rakhimov,

Safin

et al. 2023

IEEE Access

View full text Add to dashboard Cite

We present an approach for the reconstruction of textured 3D meshes of human heads from one or few views. Since such few-shot reconstruction is underconstrained, it requires prior knowledge which is hard to impose on traditional 3D reconstruction algorithms. In this work, we rely on the recently introduced 3D representation -neural implicit functions -which, being based on neural networks, allows to naturally learn priors about human heads from data, and is directly convertible to textured mesh. Namely, we extend NeuS, a state-of-the-art neural implicit function formulation, to represent multiple objects of a class (human heads in our case) simultaneously. The underlying neural net architecture is designed to learn the commonalities among these objects and to generalize to unseen ones. Our model is trained on just a hundred smartphone videos and does not require any scanned 3D data. Afterwards, the model can fit novel heads in the few-shot or one-shot modes with good results.INDEX TERMS 3D portraits, 3D reconstruction, few-shot, head reconstruction, meta-learning, neural implicit functions• We introduce a new type of 3D neural implicit architecture

show abstract

Section: Few-or Single-view Head Reconstructionmentioning

confidence: 99%

Multi-NeuS: 3D Head Portraits From Single Image With Neural Implicit Functions

Burkov,

Rakhimov,

Safin

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For instance, 3D facial templates were used in [33,34], but they were highly dependant on the template's demographic. Most recent works based on photometric stereo methods [35,36,37] combined their power to capture fine details with the capacity of 3DMMs to model global shape variations, obtaining impressive results.…”

Section: Traditional Approachesmentioning

confidence: 99%

BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs

Morales¹,

Porras²,

Linguraru³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a 3D face reconstruction system that aims at recovering the 3D facial geometry of babies from uncalibrated photographs, BabyNet. Since the 3D facial geometry of babies differs substantially from that of adults, baby-specific facial reconstruction systems are needed. BabyNet consists of two stages: 1) a 3D graph convolutional autoencoder learns a latent space of the baby 3D facial shape; and 2) a 2D encoder that maps photographs to the 3D latent space based on representative features extracted using transfer learning. In this way, using the pre-trained 3D decoder, we can recover a 3D face from 2D images. We evaluate BabyNet and show that 1) methods based on adult datasets cannot model the 3D facial geometry of babies, which proves the need for a babyspecific method, and 2) BabyNet outperforms classical model-fitting methods even when a baby-specific 3D morphable model, such as BabyFM, is used.

show abstract