Wavelet Model-based Stereo for Fast, Robust Face Reconstruction

Brunton, Alan; Lang, Jochen; Dubois, Éric; Shu, Chang

doi:10.1109/crv.2011.53

Cited by 12 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This native 3D approach was guided by manually placed landmarks to ensure good convergence. Brunton et al (2011) adopt wavelet bases to model independent prior distributions at multiple scales for the 3D facial shape. This offers a natural way to represent and combine localized shape variations in different facial areas.…”

Section: Previous Workmentioning

confidence: 99%

Large Scale 3D Morphable Models

et al. 2017

View full text Add to dashboard Cite

We present large scale facial model (LSFM)-a 3D Morphable Model (3DMM) automatically constructed from 9663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, containing statistical information from a huge variety of the human population. To build such a large model we introduce a novel fully automated and robust Morphable Model construction pipeline, informed by an evaluation of state-of-the-art dense correspondence techniques. The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM model but also models tailored for specific age, gender or ethnicity groups. We utilize the proposed model to perform age classification from 3D shape alone and to reconstruct noisy out-of-sample data in the low-dimensional model space. Furthermore, we perform a systematic analysis of the constructed 3DMM models that showcases their quality and descriptive power. reveal that the proposed 3DMM achieves state-of-the-art results, outperforming existing models by a large margin. Finally, for the benefit of the research community, we make publicly available the source code of the proposed automatic 3DMM construction pipeline, as well as the constructed global 3DMM and a variety of bespoke models tailored by age, gender and ethnicity.

show abstract

Section: Previous Workmentioning

confidence: 99%

Large Scale 3D Morphable Models

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In contrast, by applying a wavelet transform to the data first, statistical models can be constructed that capture shape variation in both a local and multi-scale way. Such wavelet-domain techniques have been used extensively for medical imaging [12,20,17], and Brunton et al [8] proposed a method to analyze local shape differences of 3D faces in neutral expression in a hierarchical way. This method decomposes each face hierarchically using a wavelet transform and learns a PCA model for each wavelet coefficient independently.…”

Section: Related Workmentioning

confidence: 99%

“…When combined with subsampling, the transform can be computed in time linear in the number of vertices. The particular wavelet decomposition we use [3] follows Catmull-Clark subdivision, and has been used previously for localized statistical models in multiple application domains [17,8]. The wavelet transform is a linear operator, denoted D. For a 3D face surface X , the wavelet coefficients are s = DX .…”

Section: Second Generation Spherical Waveletsmentioning

confidence: 99%

Multilinear Wavelets: A Statistical Shape Space for Human Faces

Brunton

Bolkart

Wuhrer

2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

We present a statistical model for 3D human faces in varying expression, which decomposes the surface of the face using a wavelet transform, and learns many localized, decorrelated multilinear models on the resulting coefficients. Using this model we are able to reconstruct faces from noisy and occluded 3D face scans, and facial motion sequences. Accurate reconstruction of face shape is important for applications such as tele-presence and gaming. The localized and multi-scale nature of our model allows for recovery of fine-scale detail while retaining robustness to severe noise and occlusion, and is computationally efficient and scalable. We validate these properties experimentally on challenging data in the form of static scans and motion sequences. We show that in comparison to a global multilinear model, our model better preserves fine detail and is computationally faster, while in comparison to a localized PCA model, our model better handles variation in expression, is faster, and allows us to fix identity parameters for a given subject.

show abstract

“…Of course, the results in the second case are much better, since the facial landmarks it needs are obtained in 3D, so their position is very reliable. Another technique, in this case, a semi-automatic one, is the one by Brunton et al [5], who obtain very accurate facial meshes by using wavelets in a Bayesian environment. There are also systems which need a database to be able to reconstruct the 3D face.…”

Section: Previous Workmentioning

confidence: 99%

3D facial merging for virtual human reconstruction

Pagés

Morán

2012

2012 3dtv-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3dtv-Con)

View full text Add to dashboard Cite

There is an increasing need of easy and affordable technologies to automatically generate virtual 3D models from their real counterparts. In particular, 3D human reconstruction has driven the creation of many clever techniques, most of them based on the visual hull (VH) concept. Such techniques do not require expensive hardware; however, they tend to yield 3D humanoids with realistic bodies but mediocre faces, since VH cannot handle concavities. On the other hand, structured light projectors allow to capture very accurate depth data, and thus to reconstruct realistic faces, but they are too expensive to use several of them. We have developed a technique to merge a VH-based 3D mesh of a reconstructed humanoid and the depth data of its face, captured by a single structured light projector. By combining the advantages of both systems in a simple setting, we are able to reconstruct realistic 3D human models with believable faces.Index Terms -3D reconstruction, human 3D models, visual hull, structured light, 3D mesh merging.

show abstract

Wavelet Model-based Stereo for Fast, Robust Face Reconstruction

Cited by 12 publications

References 27 publications

Large Scale 3D Morphable Models

Large Scale 3D Morphable Models

Multilinear Wavelets: A Statistical Shape Space for Human Faces

3D facial merging for virtual human reconstruction

Contact Info

Product

Resources

About