Different features of skin are associated with various medical conditions and provide opportunities to evaluate and monitor body health. This study created a strategy to assess choroidal thinning through the video analysis of facial skin. Videos capturing the entire facial skin were collected from 48 participants with age-related macular degeneration (AMD) and 12 healthy individuals. These facial videos were analyzed using video-based trans-angiosomes imaging photoplethysmography (TaiPPG) to generate facial imaging biomarkers that were correlated with choroidal thickness (CT) measurements. The CT of all patients was determined using swept-source optical coherence tomography (SS-OCT). The results revealed the relationship between relative blood pulsation amplitude (BPA) in three typical facial angiosomes (cheek, side-forehead and mid-forehead) and the average macular CT (r = 0.48, p < 0.001; r = -0.56, p < 0.001; r = -0.40, p < 0.01). When considering a diagnostic threshold of 200{\mu}m, the newly developed facial video analysis tool effectively distinguished between cases of choroidal thinning and normal cases, yielding areas under the curve of 0.75, 0.79 and 0.69. These findings shed light on the connection between choroidal blood flow and facial skin hemodynamics, which suggests the potential for predicting vascular diseases through widely accessible skin imaging data.
Multimodal deep learning methods capture synergistic features from multiple modalities and have the potential to improve accuracy for stress detection compared to unimodal methods. However, this accuracy gain typically comes from high computational cost due to the high-dimensional feature spaces, especially for intermediate fusion. Dimensionality reduction is one way to optimize multimodal learning by simplifying data and making the features more amenable to processing and analysis, thereby reducing computational complexity. This paper introduces an intermediate multimodal fusion network with manifold learning-based dimensionality reduction. The multimodal network generates independent representations from biometric signals and facial landmarks through 1D-CNN and 2D-CNN. Finally, these features are fused and fed to another 1D-CNN layer, followed by a fully connected dense layer. We compared various dimensionality reduction techniques for different variations of unimodal and multimodal networks. We observe that the intermediate-level fusion with the Multi-Dimensional Scaling (MDS) manifold method showed promising results with an accuracy of 96.00\% in a Leave-One-Subject-Out Cross-Validation (LOSO-CV) paradigm over other dimensional reduction methods. MDS had the highest computational cost among manifold learning methods. However, while outperforming other networks, it managed to reduce the computational cost of the proposed networks by 25\% when compared to six well-known conventional feature selection methods used in the preprocessing step.
The synthesis of 3D facial animations from speech has garnered considerable attention. Due to the scarcity of high-quality 4D facial data and well-annotated abundant multi-modality labels, previous methods often suffer from limited realism and a lack of lexible conditioning. We address this challenge through a trilogy. We first introduce Generalized Neural Parametric Facial Asset (GNPFA), an efficient variational auto-encoder mapping facial geometry and images to a highly generalized expression latent space, decoupling expressions and identities. Then, we utilize GNPFA to extract high-quality expressions and accurate head poses from a large array of videos. This presents the M2F-D dataset, a large, diverse, and scan-level co-speech 3D facial animation dataset with well-annotated emotional and style labels. Finally, we propose Media2Face, a diffusion model in GNPFA latent space for co-speech facial animation generation, accepting rich multi-modality guidances from audio, text, and image. Extensive experiments demonstrate that our model not only achieves high fidelity in facial animation synthesis but also broadens the scope of expressiveness and style adaptability in 3D facial animation.
Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands in terms of learning data; 2) the difficulties in generalising between different domains; and 3) the lack of interpretability/explainability, with biometrics being of particular interest, as it is important to provide evidence able to be used for forensics/legal purposes (e.g., in courts). To the best of our knowledge, this paper describes the first recognition framework/strategy that aims at addressing the three weaknesses simultaneously. At first, it relies exclusively in synthetic samples for learning purposes. Instead of requiring a large amount and variety of samples for each subject, the idea is to exclusively enroll a 3D point cloud per identity. Then, using generative strategies, we synthesize a very large (potentially infinite) number of samples, containing all the desired covariates (poses, clothing, distances, perspectives, lighting, occlusions,...). Upon the synthesizing method used, it is possible to adapt precisely to different kind of domains, which accounts for generalization purposes. Such data are then used to learn a model that performs local registration between image pairs, establishing positive correspondences between body parts that are the key, not only to recognition (according to cardinality and distribution), but also to provide an interpretable description of the response (e.g.: "both samples are from the same person, as they have similar facial shape, hair color and legs thickness").
This technical report presents a diffusion model based framework for face swapping between two portrait images. The basic framework consists of three components, i.e., IP-Adapter, ControlNet, and Stable Diffusion's inpainting pipeline, for face feature encoding, multi-conditional generation, and face inpainting respectively. Besides, I introduce facial guidance optimization and CodeFormer based blending to further improve the generation quality. Specifically, we engage a recent light-weighted customization method (i.e., DreamBooth-LoRA), to guarantee the identity consistency by 1) using a rare identifier "sks" to represent the source identity, and 2) injecting the image features of source portrait into each cross-attention layer like the text features. Then I resort to the strong inpainting ability of Stable Diffusion, and utilize canny image and face detection annotation of the target portrait as the conditions, to guide ContorlNet's generation and align source portrait with the target portrait. To further correct face alignment, we add the facial guidance loss to optimize the text embedding during the sample generation.
In this work, we tackle the challenge of enhancing the realism and expressiveness in talking head video generation by focusing on the dynamic and nuanced relationship between audio cues and facial movements. We identify the limitations of traditional techniques that often fail to capture the full spectrum of human expressions and the uniqueness of individual facial styles. To address these issues, we propose EMO, a novel framework that utilizes a direct audio-to-video synthesis approach, bypassing the need for intermediate 3D models or facial landmarks. Our method ensures seamless frame transitions and consistent identity preservation throughout the video, resulting in highly expressive and lifelike animations. Experimental results demonsrate that EMO is able to produce not only convincing speaking videos but also singing videos in various styles, significantly outperforming existing state-of-the-art methodologies in terms of expressiveness and realism.
We present a new approach for video-driven animation of high-quality neural 3D head models, addressing the challenge of person-independent animation from video input. Typically, high-quality generative models are learned for specific individuals from multi-view video footage, resulting in person-specific latent representations that drive the generation process. In order to achieve person-independent animation from video input, we introduce an LSTM-based animation network capable of translating person-independent expression features into personalized animation parameters of person-specific 3D head models. Our approach combines the advantages of personalized head models (high quality and realism) with the convenience of video-driven animation employing multi-person facial performance capture. We demonstrate the effectiveness of our approach on synthesized animations with high quality based on different source videos as well as an ablation study.
The face expression is the first thing we pay attention to when we want to understand a person's state of mind. Thus, the ability to recognize facial expressions in an automatic way is a very interesting research field. In this paper, because the small size of available training datasets, we propose a novel data augmentation technique that improves the performances in the recognition task. We apply geometrical transformations and build from scratch GAN models able to generate new synthetic images for each emotion type. Thus, on the augmented datasets we fine tune pretrained convolutional neural networks with different architectures. To measure the generalization ability of the models, we apply extra-database protocol approach, namely we train models on the augmented versions of training dataset and test them on two different databases. The combination of these techniques allows to reach average accuracy values of the order of 85\% for the InceptionResNetV2 model.
While state-of-the-art facial expression recognition (FER) classifiers achieve a high level of accuracy, they lack interpretability, an important aspect for end-users. To recognize basic facial expressions, experts resort to a codebook associating a set of spatial action units to a facial expression. In this paper, we follow the same expert footsteps, and propose a learning strategy that allows us to explicitly incorporate spatial action units (aus) cues into the classifier's training to build a deep interpretable model. In particular, using this aus codebook, input image expression label, and facial landmarks, a single action units heatmap is built to indicate the most discriminative regions of interest in the image w.r.t the facial expression. We leverage this valuable spatial cue to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with \aus map. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with aus maps, simulating the experts' decision process. This is achieved using only the image class expression as supervision and without any extra manual annotations. Moreover, our method is generic. It can be applied to any CNN- or transformer-based deep classifier without the need for architectural change or adding significant training time. Our extensive evaluation on two public benchmarks RAFDB, and AFFECTNET datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on Class-Activation Mapping methods (CAMs), and we show that our training technique improves the CAM interpretability.
Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the generalization capabilities of recent image editing approaches remain constrained. In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-context learning capability and unifying language instruction. This framework incorporates a module specifically optimized for image editing tasks, leveraging the VMamba Block and an editing-shift matching strategy to augment in-context learning. Furthermore, we unveil a selective area-matching technique specifically engineered to address and rectify corrupted details in generated images, such as human facial features, to further improve the quality. Another key innovation of our approach is the integration of a language unification technique, which aligns language embeddings with editing semantics to elevate the quality of image editing. Moreover, we compile the first dataset for image editing with visual prompts and editing instructions that could be used to enhance in-context capability. Trained on this dataset, our methodology not only achieves superior synthesis quality for trained tasks, but also demonstrates robust generalization capability across unseen vision tasks through tailored prompts.