Date: November 2011.
Source: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, pp 2296–2303.
Abstract: This paper presents the first dynamic-3D/4D FACS data set for facial expression research, containing 10 subjects performing between 19 and 97 different AUs both individually and in combination. In total the corpus contains 519 AU sequences. The peak expression frame of each sequence has been manually FACS coded by certified FACS experts. This provides a ground truth for 3D FACS based AU recognition systems. In order to use this data, we describe the first framework for building dynamic 3D morphable models. This includes a novel Active Appearance Model (AAM) based 3D facial registration and mesh correspondence scheme. The approach overcomes limitations in existing methods that require facial markers or are prone to optical flow drift. We provide the first quantitative assessment of such 3D facial mesh registration techniques and show how our proposed method provides more reliable correspondence.
3dMD’s Role: D3DFACS, the first dynamic 3D FACS dataset for facial expression research, was captured using a dynamic-3D/4D 3dMDface System with 2 Modular Camera Units (MCUs) each including a stereo camera pair, a color camera, and a speckle projector, recording at 60fps. The dataset contains 10 subjects performing between 19 and 97 facial action units each, totaling 519 3dMD image sequences, later becoming a direct input into the FLAME facial model.
Article: A FACS Valid 3D Dynamic Action Unit Database with Applications to 3D Dynamic Morphable Facial Modeling.
Authors: Darren Cosker, Eva Krumhuber, Adrian Hilton. University of Surrey.