Abstract
We present a practical approach to capturing ear-to-ear face models comprising both 3D meshes and intrinsic textures (i.e. diffuse and specular albedo and normal maps). Our approach is a hybrid of geometric and photometric methods
and requires no geometric calibration. Photometric measurements made in a lightstage are used to estimate view dependent high resolution normal maps. We overcome problems of fixed photometric viewpoint by capturing in multiple poses. We use a multiview reconstruction pipeline of structure-from-motion followed by multiview stereo to compute a base mesh to which the photometric views are registered. We propose a novel approach to robustly stitching the normal maps and intrinsic textures into a seamless, complete and detailed face model. The resulting models provide photorealistic renderings in any view.
and requires no geometric calibration. Photometric measurements made in a lightstage are used to estimate view dependent high resolution normal maps. We overcome problems of fixed photometric viewpoint by capturing in multiple poses. We use a multiview reconstruction pipeline of structure-from-motion followed by multiview stereo to compute a base mesh to which the photometric views are registered. We propose a novel approach to robustly stitching the normal maps and intrinsic textures into a seamless, complete and detailed face model. The resulting models provide photorealistic renderings in any view.
Original language | English |
---|---|
Publisher | arXiv |
Number of pages | 14 |
Publication status | E-pub ahead of print - 17 Dec 2016 |
Keywords
- Diffuse albedo
- specular albedo
- photometric stereo
- multiview stereo
- face capture
Fingerprint
Dive into the research topics of 'Ear-to-ear Capture of Facial Intrinsics'. Together they form a unique fingerprint.Profiles
-
Bernie Tiddeman
- Faculty of Business and Physical Sciences, Department of Computer Science - Professor in Computer Science
Person: Teaching And Research