Search

We propose a novel joint framework for 3D face reconstruction (3DFR) that integrates facial attribute estimation (FAE) as an auxiliary task. One of the essential problems of 3DFR is to extract semantic facial features (e.g., Big Nose, High Cheekbones, and Asian) from in-the-wild 2D images, which is inherently involved with FAE. These two tasks, though heterogeneous, are highly relevant to each other. To achieve this, we leverage a Convolutional Neural Network to extract shared facial representations for both shape decoder and attribute classifier. We further develop an in-batch hybrid-task training scheme that enables our model to learn from heterogeneous facial datasets jointly within a mini-batch. Thanks to the joint loss that provides supervision from both 3DFR and FAE domains, our model learns the correlations between 3D shapes and facial attributes, which benefit both feature extraction and shape inference. Quantitative evaluation and qualitative visualization results confirm the effectiveness and robustness of our joint framework.

3D Morphable Model (3DMM) is a statistical tool widely employed in reconstructing 3D face shape. Existing methods are aimed at predicting 3DMM shape parameters with a single encoder but suffer from unclear distinction of different attributes. To address this problem, Two-Pathway Encoder-Decoder Network (2PEDN) is proposed to regress the identity and expression components via global and local pathways. Specifically, each 2D face image is cropped into global face and local details as the inputs for the corresponding pathways. 2PEDN is trained to predict 3D face shape components with two sets of loss functions designed to supervise 3D face reconstruction error and face identification error. To reduce the conflict between abundant facial details and saving computer storage space, a magnitudes converter is devised. Experiments demonstrate that the proposed method outperforms several 3D face recontruction methods.

To investigate the clinical characteristics and common etiology of vertigo.The clinical data of 168 patients with vertigo in the department of otolaryngolology and neurology from December 2007 to March 2009 were retrospectively analyzed The patients were inquired and examined by pure tone average thresholds, videonystagmography, Dix-Hallpike test, cervical spine X-ray, skull CT and (or) MRI and transcranial Doppler.One hundred and thirty-four patients with vertigo were of peripheral origin, with 66 cases benign paroxysmal positional vertigo, 30 cases Meniere's disease, 24 cases sudden deafness, 5 cases vestibular neuritis, 5 cases otitis media ,2 cases ear herpes zosters and 2 cases ototoxicity. Among 26 patients with vertigo of central, 20 patients were vertebrobasilar TIA.The most common etiology of the vestibular peripheral vertigo is the benign paroxysmal positional vertigo. Detailed history and the features of vertigo, particular about the duration of vertigo and hearing change, may provide the important evidences for the accurate diagnosis and differential diagnosis of vertigo.