Search

Abstract Artificially created human faces play an increasingly important role in our digital world. However, the so-called uncanny valley effect may cause people to perceive highly, yet not perfectly human-like faces as eerie, bringing challenges to the interaction with virtual agents. At the same time, the neurocognitive underpinnings of the uncanny valley effect remain elusive. Here, we utilized an electroencephalography (EEG) dataset of steady-state visual evoked potentials (SSVEP) in which participants were presented with human face images of different stylization levels ranging from simplistic cartoons to actual photographs. Assessing neuronal responses both in frequency and time domain, we found a non-linear relationship between SSVEP amplitudes and stylization level, that is, the most stylized cartoon images and the real photographs evoked stronger responses than images with medium stylization. Moreover, realness of even highly similar stylization levels could be decoded from the EEG data with task-related component analysis (TRCA). Importantly, we also account for confounding factors, such as the size of the stimulus face’s eyes, which previously have not been adequately addressed. Together, this study provides a basis for future research and neuronal benchmarking of real-time detection of face realness regarding three aspects: SSVEP-based neural markers, efficient classification methods, and low-level stimulus confounders.

Abstract Flap loss through limited perfusion remains a major complication in reconstructive surgery. Continuous monitoring of perfusion will facilitate early detection of insufficient perfusion. Remote or imaging photoplethysmography (rPPG/iPPG) as a non-contact, non-ionizing, and non-invasive monitoring technique provides objective and reproducible information on physiological parameters. The aim of this study is to establish rPPG for intra- and postoperative monitoring of flap perfusion in patients undergoing reconstruction with free fasciocutaneous flaps (FFCF). We developed a monitoring algorithm for flap perfusion, which was evaluated in 15 patients. For 14 patients, ischemia of the FFCF in the forearm and successful reperfusion of the implanted FFCF was quantified based on the local signal. One FFCF showed no perfusion after reperfusion and devitalized in the course. Intraoperative monitoring of perfusion with rPPG provides objective and reproducible results. Therefore, rPPG is a promising technology for standard flap perfusion monitoring on low costs without the need for additional monitoring devices.

This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric model for accurate capturing and realistic synthesis of facial expressions from a latent feature vector. Our animation method is based on a conditional CNN that transforms text or speech into a sequence of animation parameters. In contrast to previous approaches, our animation model learns disentangling/synthesizing different acting-styles in an unsupervised manner, requiring only phonetic labels that describe the content of training sequences. For realistic real-time rendering, we train a U-Net that refines rasterization-based renderings by computing improved pixel colors and a foreground matte. We compare our framework qualitatively/quantitatively against recent methods for head modeling as well as facial animation and evaluate the perceived rendering/animation quality in a user-study, which indicates large improvements compared to state-of-the-art approaches.

Abstract Accurate and temporally consistent modeling of human bodies is essential for a wide range of applications, including character animation, understanding human social behavior, and AR/VR interfaces. Capturing human motion accurately from a monocular image sequence remains challenging; modeling quality is strongly influenced by temporal consistency of the captured body motion. Our work presents an elegant solution to integrating temporal constraints during fitting. This increases both temporal consistency and robustness during optimization. In detail, we derive parameters of a sequence of body models, representing shape and motion of a person. We optimize these parameters over the complete image sequence, fitting a single consistent body shape while imposing temporal consistency on the body motion, assuming body joint trajectories to be linear over short time. Our approach enables the derivation of realistic 3D body models from image sequences, including jaw pose, facial expression, and articulated hands. Our experiments show that our approach accurately estimates body shape and motion, even for challenging movements and poses. Further, we apply it to the particular application of sign language analysis, where accurate and temporally consistent motion modelling is essential, and show that the approach is well-suited to this kind of application.

We investigate an edge-computing scenario for robot control, where two similar neural networks are running on one computational node. We test the feasibility of using a single object-detection model (YOLOv5) with the benefit of reduced computational resources against the potentially more accurate independent and specialized models. Our results show that using one single convolutional neural network (for object detection and hand-gesture classification) instead of two separate ones can reduce resource usage by almost 50%. For many classes, we observed an increase in accuracy when using the model trained with more labels. For small datasets (a few hundred instances per label), we found that it is advisable to add labels with many instances from another dataset to increase detection accuracy.

An end‐to‐end pipeline for the creation of high‐quality animatable volumetric video of human performances is presented. Going beyond the application of free‐viewpoint video, the authors allow re‐animation and alteration of an actor's performance through the enrichment of the captured data with semantics and animation properties. Hybrid geometry‐ and video‐based animation methods are applied that allow a direct animation of the high‐quality data itself instead of creating a CG model that resembles the captured data. Semantic enrichment and animation are achieved by establishing temporal consistency followed by automatic rigging of each 3D frame using a parametric human body model. The hybrid approach combines the flexibility of classical CG animation with the realism of real captured data. For the face, coarse movements are modelled in the geometry only, while very fine and subtle details, often lacking in purely geometric methods, are captured in video textures, which can interactively be combined to form new facial expressions. On top of that, regions that are challenging to synthesise, such as the teeth or the eyes, are learned and filled in realistically in an autoencoder‐based approach. This study covers the full pipeline from capturing, volumetric video production, and enrichment with semantics for the final hybrid animation.

Creating realistic animations of human faces is still a challenging task in computer graphics. While computer graphics (CG) models capture much variability in a small parameter vector, they usually do not meet the necessary visual quality. This is due to the fact, that geometry‐based animation often does not allow fine‐grained deformations and fails in difficult areas (mouth, eyes) to produce realistic renderings. Image‐based animation techniques avoid these problems by using dynamic textures that capture details and small movements that are not explained by geometry. This comes at the cost of high‐memory requirements and limited flexibility in terms of animation because dynamic texture sequences need to be concatenated seamlessly, which is not always possible and prone to visual artefacts. In this study, the authors present a new hybrid animation framework that exploits recent advances in deep learning to provide an interactive animation engine that can be used via a simple and intuitive visualisation for facial expression editing. The authors describe an automatic pipeline to generate training sequences that consist of dynamic textures plus sequences of consistent three‐dimensional face models. Based on this data, they train a variational autoencoder to learn a low‐dimensional latent space of facial expressions that is used for interactive facial animation.

Multimodal user interfaces promise natural and intuitive human–machine interactions. However, is the extra effort for the development of a complex multisensor system justified, or can users also be satisfied with only one input modality? This study investigates interactions in an industrial weld inspection workstation. Three unimodal interfaces, including spatial interaction with buttons augmented on a workpiece or a worktable, and speech commands, were tested individually and in a multimodal combination. Within the unimodal conditions, users preferred the augmented worktable, but overall, the interindividual usage of all input technologies in the multimodal condition was ranked best. Our findings indicate that the implementation and the use of multiple input modalities is valuable and that it is difficult to predict the usability of individual input modalities for complex systems.

Detecting morphed face images has become an important task to maintain the trust in automated verification systems based on facial images, e.g., at automated border control gates. Deep Neural Network (DNN)-based detectors have shown remarkable results, but without further investigations their decision-making process is not transparent. In contrast to approaches based on hand-crafted features, DNNs have to be analyzed in complex experiments to know which characteristics or structures are generally used to distinguish between morphed and genuine face images or considered for an individual morphed face image. In this paper, we present Feature Focus, a new transparent face morphing detector based on a modified VGG-A architecture and an additional feature shaping loss function, as well as Focused Layer-wise Relevance Propagation (FLRP), an extension of LRP. FLRP in combination with the Feature Focus detector forms a reliable and accurate explainability component. We study the advantages of the new detector compared to other DNN-based approaches and evaluate LRP and FLRP regarding their suitability for highlighting traces of image manipulation from face morphing. To this end, we use partial morphs which contain morphing artifacts in predefined areas only and analyze how much of the overall relevance each method assigns to these areas.

Abstract In this paper, we present a novel approach for assessing and interacting with surface tracking algorithms targeting video manipulation in post-production. As tracking inaccuracies are unavoidable, we enable the user to provide small hints to the algorithms instead of correcting erroneous results afterwards. Based on 2D mesh warp-based optical flow estimation, we visualize results and provide tools for user feedback in a consistent reference system, texture space. In this space, accurate tracking results are reflected by static appearance, and errors can easily be spotted as apparent change. A variety of established tools can be utilized to visualize and assess the change between frames. User interaction to improve tracking results becomes more intuitive in texture space, as it can focus on a small region rather than a moving object. We show how established tools can be implemented for interaction in texture space to provide a more intuitive interface allowing more effective and accurate user feedback.

One of the main challenges for the implementation of artificial intelligence (AI) in agriculture includes the low replicability and the corresponding difficulty in systematic data gathering, as no two fields are exactly alike. Therefore, the comparison of several pilot experiments in different fields, weather conditions and farming techniques enhances the collective knowledge. Thus, this work provides a summary of the most recent research activities in the form of research projects implemented and validated by the authors in several European countries, with the objective of presenting the already achieved results, the current investigations and the still open technical challenges. As an overall conclusion, it can be mentioned that even though in their primary stages in some cases, AI technologies improve decision support at farm level, monitoring conditions and optimizing production to allow farmers to apply the optimal number of inputs for each crop, thereby boosting yields and reducing water use and greenhouse gas emissions. Future extensions of this work will include new concepts based on autonomous and intelligent robots for plant and soil sample retrieval, and effective livestock management.

We develop a stereo-multispectral endoscopic prototype in which a filter-wheel is used for surgical guidance to remove cholesteatoma tissue in the middle ear. Cholesteatoma is a destructive proliferating tissue. The only treatment for this disease is surgery. Removal is a very demanding task, even for experienced surgeons. It is very difficult to distinguish between bone and cholesteatoma. In addition, it can even reoccur if not all tissue particles of the cholesteatoma are removed, which leads to undesirable follow-up operations. Therefore, we propose an image-based method that combines multispectral tissue classification and 3D reconstruction to identify all parts of the removed tissue and determine their metric dimensions intraoperatively. The designed multispectral filter-wheel 3D-endoscope prototype can switch between narrow-band spectral and broad-band white illumination, which is technically evaluated in terms of optical system properties. Further, it is tested and evaluated on three patients. The wavelengths 400 nm and 420 nm are identified as most suitable for the differentiation task. The stereoscopic image acquisition allows accurate 3D surface reconstruction of the enhanced image information. The first results are promising, as the cholesteatoma can be easily highlighted, correctly identified, and visualized as a true-to-scale 3D model showing the patient-specific anatomy.