Search

In the process of reconstructing a historical event such as a rock concert only from video, the reconstruction of faces and expressions of the musicians is obviously important. However, in the process of rebuilding appearance, because of the low quality of the video of the recorded concert, the result of the reconstruction may be far from the real appearance. In this paper, a robust 3D face reconstruction application is described that can be applied to a video recording. The application first uses DeblurGAN program to run anti-ambiguity calculation and removes the ambiguity in the concert video. Then, the super-resolution program is used to enlarge every frame of the concert video by four times, thus making every frame of the video clearer. Finally, the 3D faces are obtained after 3D reconstruction of the processed video frames via the 3DMM_CNN program.&nbsp

Given an uncalibrated network of video cameras, we are tasked with the problem of building a 3D model of every person's face as they move within the network. The process of doing so requires overcoming many challenges including person detection, tracking, cross-camera correspondence (how to determine if a person in one camera is the same person in another), and the final 3D model reconstruction from multiple views in real-time or at near real-time speeds (efficient modeling and data fusion from multiple hardware sources). Towards this goal, a wireless camera network was designed and built from the ground up, a new tracking algorithm and a cross-camera human signature method was developed, and face modeling using multiple cameras in a real-world setting was performed.

This study proposes a novel automatic method for facial landmark localization relying on geometrical properties of 3D facial surface working both on complete faces displaying different emotions and in presence of occlusions. In particular, 12 descriptors coming from Differential Geometry including the coefficients of the fundamental forms, Gaussian, mean, principal curvatures, shape index and curvedness are extracted as facial features and their local geometric properties are exploited to localize 13 soft-tissue landmarks from eye and nose areas. The method is deterministic and is backboned by a thresholding technique designed by studying the behaviour of each geometrical descriptor in correspondence to the locus of each landmark. Occlusions are managed by a detection algorithm based on geometrical properties which allows to proceed with the landmark localization avoiding the covered areas. Experimentations were carried out on 3132 faces of the Bosphorus database and of a 230-sized internal database, including expressive and occluded ones (mouth, eye, and eyeglasses occlusions), obtaining 4.75 mm mean localization error.

Recent Face Analysis advances have focused the attention on studying and formalizing 3D facial shape. Landmarks, i.e. typical points of the face, are perfectly suited to the purpose, as their position on visage shape allows to build up a map of each human being’s appearance. This turns to be extremely useful for a large variety of fields and related applications. In particular, the forensic context is taken into consideration in this study. This work is intended as a survey of current research advances in forensic science involving 3D facial landmarks. In particular, by selecting recent scientific contributions in this field, a literature review is proposed for in-depth analyzing which landmarks are adopted, and how, in this discipline. The main outcome concerns the identification of a leading research branch, which is landmark-based facial reconstruction from skull. The choice of selecting 3D contributions is driven by the idea that the most innovative Face Analysis research trends work on three-dimensional data, such as depth maps and meshes, with three-dimensional software and tools. The third dimension improves the accurateness and is robust to colour and lightning variations.

In the last decade, three-dimensional landmarking has gained attention for different applications, such as face recognition for both identification of suspects and authentication, facial expression recognition, corrective and aesthetic surgery, syndrome study and diagnosis. This work focuses on the last one by proposing a geometrically-based landmark extraction algorithm aimed at diagnosing syndromes on babies before their birth. Pivotal role in this activity is the support provided by physicians and 3D ultrasound tools for working on real faces. In particular, the landmarking algorithm here proposed only relies on descriptors coming from Differential Geometry (Gaussian, mean, and principal curvatures, derivatives, coefficients of first and second fundamental forms, Shape and Curvedness indexes) and is tested on nine facial point clouds referred to nine babies taken by a three-dimensional ultrasound tool at different weeks' gestation. The results obtained, validated with the support of four practitioners, show that the localization is quite accurate. All errors lie in the range between 0 and 3.5 mm and the mean distance for each shell is in the range between 0.6 and 1.6 mm. The landmarks showing the highest errors are the ones belonging to the mouth region. Instead, the most precise landmark is the pronasal, on the nose tip, with a mean distance of 0.55 mm. Relying on current literature, this study is something missing in the state-of-the-art of the field, as present facial studies on 3D ultrasound do not work on automatic landmarking yet.

In this paper, we propose a facial feature localization algorithm based on a binary neural network technique - k-Nearest Neighbour Advanced Uncertain Reasoning Architecture (kNN AURA) to encode, train and match the feature patterns to accurate identify the nose tip in 3D. Based on the results of the 3D nose tip localization, the main face area is detected and cropped from the original 3D image. Then we present a novel framework to implement the 3D face registration by several integrated phases. First we use Principal Component Analysis (PCA) to roughly correct the server misalignment. Then we exploit the symmetric of human face to reduce the misalignment about and axis. In order to reduce the effect of facial expression variations, the expression-invariant region is segmented. Using Iterative Closest Point (ICP) algorithms, the expression-invariant region of faces can be aligned according to a standard face model, the misalignment about is then eventually corrected. Our experiments performed on the FRGC v2 database which contains pose and expression variations show that our approach outperforms the current state-of-the-art techniques both in the nose tip localization and face registration.

Dense surface registration of three-dimensional (3D) human facial images holds great potential for studies of human trait diversity, disease genetics, and forensics. Non-rigid registration is particularly useful for establishing dense anatomical correspondences between faces. Here we describe a novel non-rigid registration method for fully automatic 3D facial image mapping. This method comprises two steps: first, seventeen facial landmarks are automatically annotated, mainly via PCA-based feature recognition following 3D-to-2D data transformation. Second, an efficient thin-plate spline (TPS) protocol is used to establish the dense anatomical correspondence between facial images, under the guidance of the predefined landmarks. We demonstrate that this method is robust and highly accurate, even for different ethnicities. The average face is calculated for individuals of Han Chinese and Uyghur origins. While fully automatic and computationally efficient, this method enables high-throughput analysis of human facial feature variation., 33 pages, 6 figures, 1 table

This article describes a new dataset under construction at the Media Integration and Communication Center and the University of Florence. The dataset consists of high-resolution 3D scans of human faces along with several video sequences of varying resolution and zoom level. Each subject is recorded under various scenarios, settings and conditions. This dataset is being constructed specifically to support research on techniques that bridge the gap between 2D, appearance-based recognition techniques, and fully 3D approaches. It is designed to simulate, in a controlled fashion, realistic surveillance conditions and to probe the efficacy of exploiting 3D models in real scenarios.

3D face recognition(s) systems improve current 2D image-based approaches, but in general they are required to deal with larger amounts of data. Therefore, a compact representation of 3D faces is often crucial for a better manipulation of data, in the context of 3D face applications such as smart card identity verification systems. We propose a new compact 3D representation by focusing on the most significant parts of the face. We introduce a generative learning approach by adapting Hidden Markov Models (HMM) to work on 3D meshes. The geometry of local area around face fiducial points is modeled by training HMMs which provide a robust pose invariant point signature. Such description allows the matching by comparing the signature of corresponding points in a maximum-likelihood principle. We show that our descriptor is robust for recognizing expressions and performs faster than the current ICP-based 3D face recognition systems by maintaining a satisfactory recognition rate. Preliminary results on a subset of the FRGC 2.0 dataset are reported by considering subjects under different expressions.

International audience; In this paper, we use the three-dimensional topological shape information for human face identification. We propose a new method to represent 3D faces as a topological graph. Fine registration of surfaces is done by first automatically finding topological connected components, and then constructing its topological graph representing the important topological changes on the face. The similarity calculation between 3D faces is processed using coarse-to-fine strategy while preserving the consistency of the graph structures, which result in establishing a correspondence between the parts of faces. The experiments made with a 144 3D faces dataset show the efficiency of our approach.