High-quality single-shot capture of facial geometry

By Thabo Beeler, Bernd Bickel, Paul A. Beardsley, Bob Sumner, Markus H. Gross. ACM Transactions on Graphics, 2010

418 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/df28a1c3501b3dc31becc769e648234f44fd0356

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Adaptive 3D Face Reconstruction from Unconstrained Photo Collections (2017, background): “Index Terms—Face reconstruction, photometric stereo, unconstrained Ç”
Static and dynamic 3D facial expression recognition: A comprehensive survey (2012, methodology): “Some algorithms in use, such as that employed in [48] can take around 20 min to construct the 3Dmodel from the input image, though there are other algorithms available, for example as used in the DI4D system, that take only around 15 s/ frame.”
High resolution passive facial performance capture (2010, methodology): “Also note that fine wrinkles and pores can be added to the geometry in a post-process similar to Beeler et al. [2010], and we consider this future work.”
Realtime performance-based facial animation (2011, methodology): “All these methods involve highly specialized sensors and/or controlled studio environments [Zhang and Huang 2004; Borshukov et al. 2005; Ma et al. 2007; Beeler et al. 2010; Bradley et al. 2010].”
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies (2018, methodology): “…where people can freely move [17, 21, 44, 19]; (2) facial motion is captured at close range, mostly frontal, and assuming little global head motion [5, 24, 6, 9, 51]; (3) ﬁnger motion is also captured at very close distances from hands, where the hand regions are dominant in the sensor…”
Automatic acquisition of high-fidelity facial performances using monocular videos (2014, background): “Reconstructing high-quality face models directly from multiview images offers another possibility for marker-less motion capture [Bradley et al. 2010; Beeler et al. 2010; Beeler et al. 2011; Valgaerts et al. 2012].”
A Survey on Human Motion Analysis from Depth Data (2013, background): “Most of the work has focused so far on the acquisition of high-quality data using structured light systems [100, 101, 102, 103, 104] or passive multi-camera systems [105, 106, 101, 107] in controlled setups.”
Reconstruction of Personalized 3D Face Rigs from Monocular Video (2016, methodology): “The creation of believable face animations for virtual actors in movies and in games, or for avatars in virtual reality or teleconferencing scenarios, is a challenging task.”
Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation (2017, methodology): “Here, we propose an approach motivated by the passive-stereo facial reconstruction method suggested in [3].”
High-quality passive facial performance capture using anchor frames (2011, methodology): “The motion estimation is an extension to 2D of the matching introduced in [Beeler et al. 2010] and has the following steps: 75:4 • T.”
3D Morphable Face Models—Past, Present, and Future (2019, neutral): “These methods typically do not require the aggregation of information over time and hence offer themselves for single-shot acquisition [Beeler et al. 2010] as well as full-frame rate performance capture [Beeler et al. 2011; Bradley et al. 2010; Furukawa and Ponce 2009].”
Photorealistic Facial Texture Inference Using Deep Neural Networks (2016, background): “Until recently, the digitization of photorealistic faces has only been possible in professional studio settings, typically involving sophisticated appearance measurement devices [52, 31, 18, 3, 17] and carefully controlled lighting conditions.”
Efficient Large-Scale Stereo Matching (2010, methodology): “The bottom row shows a one Megapixel face image from the dataset of [ 26 ] and the corresponding disparity map obtained using our algorithm.”
ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation (2020, background): “[2]), it provides the potential of synthesizing high-quality gaze estimation data in the future.”