Projective structure from facial motion

Grashof, Stella; Ackermann, Hanno; Kuhnke, Felix; Östermann, Jörn; Brandt, Sami S.

doi:10.23919/mva.2017.7986860

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Computer Vision field is rich in approaches targeting this problem under different assumptions and constraints. Some of these attempts [19], [20], named Shape from Shading, approximate the image formation process and make simplified assumptions about the lighting and illumination models leading to the formation of the image, while others, known as Structure from Motion (SfM), benefit from the geometric constraints in multiple images of the same object to solve the problem [21], [22]. One common approach for addressing this task are the 3D Morphable Models (3DMMs) of the human face.…”

Section: D Face Reconstructionmentioning

confidence: 99%

Head2Head++: Deep Facial Attributes Re-Targeting

Doukas

Koujan

Sharmanska

et al. 2021

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

Section: D Face Reconstructionmentioning

confidence: 99%

Head2Head++: Deep Facial Attributes Re-Targeting

Doukas

Koujan

Sharmanska

et al. 2021

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

“…A growing line of research revolves around reconstructing the 3D geometry of the face and employing this information in further ad-hoc steps, as we do in this work. Some attempts on 3D face reconstruction [11], [12], [13], known as Shape From Shading, work on approximating the image formation process and postulate simplified assumptions about the lighting and illumination models leading to the formation of the image, while others, known as Structure from Motion (SfM), capitalise on the geometric constraints in multiple images of the same object to approach the reconstruction task [14], [15], [16]. 3D Morphable Models (3DMMs) have been researched and used substantially in the literature since the pioneering work of Blanz and Vetter [17], with many extensions [18], [19], [20].…”

Section: A 3d Face Reconstructionmentioning

confidence: 99%

Head2Head: Video-based Neural Head Synthesis

Koujan

Doukas

Roussos

et al. 2020

2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)

View full text Add to dashboard Cite

In this paper, we propose a novel machine learning architecture for facial reenactment. In particular, contrary to the model-based approaches or recent frame-based methods that use Deep Convolutional Neural Networks (DCNNs) to generate individual frames, we propose a novel method that (a) exploits the special structure of facial motion (paying particular attention to mouth motion) and (b) enforces temporal consistency. We demonstrate that the proposed method can transfer facial expressions, pose and gaze of a source actor to a target video in a photo-realistic fashion more accurately than state-of-the-art methods.

show abstract

“…We are able to temporally align sequences of 3D dynamic facial expressions with our estimated expression intensities. Temporal and spatial alignment of data is a crucial step for statistical model generation, especially for human faces and bodies [4,5,6].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Features for Facial Expression Intensity Estimation Over Time

Awiszus

GraBhof²,

Kuhnke

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Self Cite

View full text Add to dashboard Cite

The diversity of facial shapes and motions among persons is one of the greatest challenges for automatic analysis of facial expressions. In this paper, we propose a feature describing expression intensity over time, while being invariant to person and the type of performed expression. Our feature is a weighted combination of the dynamics of multiple points adapted to the overall expression trajectory. We evaluate our method on several tasks all related to temporal analysis of facial expression. The proposed feature is compared to a state-of-the-art method for expression intensity estimation, which it outperforms. We use our proposed feature to temporally align multiple sequences of recorded 3D facial expressions. Furthermore, we show how our feature can be used to reveal person-specific differences in performances of facial expressions. Additionally, we apply our feature to identify the local changes in face video sequences based on action unit labels. For all the experiments our feature proves to be robust against noise and outliers, making it applicable to a variety of applications for analysis of facial movements.

show abstract

Projective structure from facial motion

Cited by 4 publications

References 15 publications

Head2Head++: Deep Facial Attributes Re-Targeting

Head2Head++: Deep Facial Attributes Re-Targeting

Head2Head: Video-based Neural Head Synthesis

Unsupervised Features for Facial Expression Intensity Estimation Over Time

Contact Info

Product

Resources

About