High resolution passive facial performance capture

By Derek Bradley, Wolfgang Heidrich, Tiberiu Popa, Alla Sheffer. ACM Transactions on Graphics, 2010

309 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/220f6b1de39b24e2017bb0a2d80d222b8528cf9e

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

Citations in the corpus

Internet Based Morphable Model (2013, methodology): “Similarly we collected photos of adults making different facial expressions.”
Real-time expression transfer for facial reenactment (2015, background): “Another option is to capture high-quality multiview data from calibrated camera arrays [Bradley et al. 2010; Beeler et al. 2011; Valgaerts et al. 2012; Fyffe et al. 2014].”
3D Virtual worlds and the metaverse: Current status and future possibilities (2013, background): “On the visual side, capturing the actual facial expression of the user at a given moment [Chandrasiri et al. 2004; Chun et al. 2007; Bradley et al. 2010] serves as an ideal complement to aforementioned facial rendering algorithms [Jimenez et al.”
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies (2018, methodology): “…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 measurements [36, 49,…”
Self-Supervised Multi-level Face Model Learning for Monocular Reconstruction at Over 250 Hz (2017, background): “While high-quality multi-view 3D reconstruction methods [4, 13, 5, 24, 30, 69] exist, we are interested in the harder monocular reconstruction problem.”
High-quality passive facial performance capture using anchor frames (2011, unknown): “The regularized position estimate Xs for motion refinement assumes local rigidity of the surface and tries to preserve the local structure using Laplacian coordinates, as in [Bradley et al. 2010].”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, background): “First approaches [BHPS10,BGY ∗ 13] that address this challenging reconstruction problem require dense multi-view capture under controlled illumination and integrate additional contour cues into the optimization.”
Total Moving Face Reconstruction (2014, background): “stereo approaches on input coming from multiple high resolution synchronized cameras which does not require markers but assumes calibration of the cameras and controlled lighting [7,8,11] or uncontrolled lighting[42].”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, result): “[116] and compare the results with nonrigid registrations.”
Production-level facial performance capture using deep convolutional neural networks (2016, background): “…and a considerable amount of computation such as multi-view stereo or photometric reconstruction of individual input frames [Beeler et al. 2011; Bradley et al. 2010; Furukawa and Ponce 2009; Fyffe et al. 2011; Shi et al. 2014; Valgaerts et al. 2012] that often require carefully crafted 3D…”
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.”
Online modeling for realtime facial animation (2013, methodology): “This is commonly achieved using a 3D template model [Bradley et al. 2010; Valgaerts et al. 2012] or building a dynamic 3D expression model (DEM) that represents the 3D geometry of the individual facial expressions of the user [Weise et al. 2011].”
Multi-View Stereo: A Tutorial (2015, methodology): “Multiple synchronized video streams can be used to recover dense 3D structure and motion information via the same MVS principles [71, 73, 37, 46, 185].”
Practice and Theory of Blendshape Facial Models (2014, methodology): “Technique that drive a low-level representation such as a mesh or a mesh driven by skinning [Wil90,GGW ∗ 98,BPL ∗ 03,BHPS10] will not be surveyed.”
A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling (2011, methodology): “We provide the first quantitative assessment of such 3D facial mesh registration techniques and show how our proposed method provides more reliable correspondence.”