Multi-View Stereo on Consistent Face Topology

Simple item page
dc.contributor.authorFyffe, Grahamen_US
dc.contributor.authorNagano, Kokien_US
dc.contributor.authorHuynh, Locen_US
dc.contributor.authorSaito, Shunsukeen_US
dc.contributor.authorBusch, Jayen_US
dc.contributor.authorJones, Andrewen_US
dc.contributor.authorLi, Haoen_US
dc.contributor.authorDebevec, Paulen_US
dc.contributor.editorLoic Barthe and Bedrich Benesen_US
dc.date.accessioned2017-04-22T16:26:44Z
dc.date.available2017-04-22T16:26:44Z
dc.date.issued2017
dc.description.abstractWe present a multi-view stereo reconstruction technique that directly produces a complete high-fidelity head model with consistent facial mesh topology. While existing techniques decouple shape estimation and facial tracking, our framework jointly optimizes for stereo constraints and consistent mesh parameterization. Our method is therefore free from drift and fully parallelizable for dynamic facial performance capture. We produce highly detailed facial geometries with artist-quality UV parameterization, including secondary elements such as eyeballs, mouth pockets, nostrils, and the back of the head. Our approach consists of deforming a common template model to match multi-view input images of the subject, while satisfying cross-view, cross-subject, and cross-pose consistencies using a combination of 2D landmark detection, optical flow, and surface and volumetric Laplacian regularization. Since the flow is never computed between frames, our method is trivially parallelized by processing each frame independently. Accurate rigid head pose is extracted using a PCA-based dimension reduction and denoising scheme. We demonstrate high-fidelity performance capture results with challenging head motion and complex facial expressions around eye and mouth regions. While the quality of our results is on par with the current state-of-the-art, our approach can be fully parallelized, does not suffer from drift, and produces face models with production-quality mesh topologies.en_US
dc.description.number2
dc.description.sectionheadersCapturing Faces
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume36
dc.identifier.doi10.1111/cgf.13127
dc.identifier.issn1467-8659
dc.identifier.pages295-309
dc.identifier.urihttps://doi.org/10.1111/cgf.13127
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13127
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.4.1 [Computer Vision]
dc.subjectImage Processing and Computer Vision
dc.subjectScanningI.3.7 [Computer Graphics]
dc.subjectThree Dimensional Graphics and Realism
dc.subjectAnimation
dc.titleMulti-View Stereo on Consistent Face Topologyen_US
Files
Collections
36-Issue 2