(a) | (b) | (c) | (d) |
---|
We 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 param-eterization, 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 vol-umetric Laplacian regularization. Since the flow is never computed between frames, our method is trivially parallelized byprocessing each frame independently. Accurate rigid head pose is extracted using a PCA-based dimension reduction and de-noising scheme. We demonstrate high-fidelity performance capture results with challenging head motion and complex facialexpressions around eye and mouth regions. While the quality of our results is on par with the current state-of-the-art, our ap-proach can be fully parallelized, does not suffer from drift, and produces face models with production-quality mesh topologies.