Despite recent progress in 3D head avatar generation, balancing identity preservation, i.e., reconstruction, with novel poses and expressions, i.e., animation, remains a challenge. Existing methods struggle to adapt Gaussians to varying geometrical deviations across facial regions, resulting in suboptimal quality. To address this, we propose GeoAvatar, a framework for adaptive geometrical Gaussian Splatting. GeoAvatar leverages Adaptive Pre-allocation Stage (APS), an unsupervised method that segments Gaussians into rigid and flexible sets for adaptive offset regularization. Then, based on mouth anatomy and dynamics, we introduce a novel mouth structure and the part-wise deformation strategy to enhance the animation fidelity of the mouth. Finally, we propose a regularization loss for precise rigging between Gaussians and 3DMM faces. Moreover, we release DynamicFace, a video dataset with highly expressive facial motions. Extensive experiments show the superiority of GeoAvatar compared to state-of-the-art methods in reconstruction and novel animation scenarios.

We introduce an industrial Head Blending pipeline for the task of seamlessly integrating an actor's head onto a target body in digital content creation. The key challenge stems from discrepancies in head shape and hair structure, which lead to unnatural boundaries and blending artifacts. Existing methods treat foreground and back-ground as a single task, resulting in suboptimal blending quality. To address this problem, we propose CHANGER, a novel pipeline that decouples background integration from foreground blending. By utilizing chroma keying for artifact-free background generation and introducing Head shape and long Hair augmentation (H2augmen-tation) to simulate a wide range of head shapes and hair styles, CHANGER improves generalization on innumerable various real-world cases. Furthermore, our Fore-ground Predictive Attention Transformer (FPAT) module enhances foreground blending by predicting and focusing on key head and body regions. Quantitative and qualitative evaluations on benchmark datasets demonstrate that our CHANGER outperforms state-of-the-art methods, de-livering high-fidelity, industrial-grade results.

Fluorescence imaging-based diagnostic systems have been widely used to diagnose skin diseases due to their ability to provide detailed information related to the molecular composition of the skin compared to conventional RGB imaging. In addition, recent advances in smartphones have made them suitable for application in biomedical imaging, and therefore various smartphone-based optical imaging systems have been developed for mobile healthcare. However, an advanced analysis algorithm is required to improve the diagnosis of skin diseases. Various deep learning-based algorithms have recently been developed for this purpose. However, deep learning-based algorithms using only white-light reflectance RGB images have exhibited limited diagnostic performance. In this study, we developed an auxiliary deep learning network called fluorescence-aided amplifying network (FAA-Net) to diagnose skin diseases using a developed multi-modal smartphone imaging system that offers RGB and fluorescence images. FAA-Net is equipped with a meta-learning-based algorithm to solve problems that may occur due to the insufficient number of images acquired by the developed system. In addition, we devised a new attention-based module that can learn the location of skin diseases by itself and emphasize potential disease regions, and incorporated it into FAA-Net. We conducted a clinical trial in a hospital to evaluate the performance of FAA-Net and to compare various evaluation metrics of our developed model and other state-of-the-art models for the diagnosis of skin diseases using our multi-modal system. Experimental results demonstrated that our developed model exhibited an 8.61% and 9.83% improvement in mean accuracy and area under the curve in classifying skin diseases, respectively, compared with other advanced models.

We developed a forward-looking (FL) multimodal endoscopic system that offers color, spectral classified, high-frequency ultrasound (HFUS) B-mode, and integrated backscattering coefficient (IBC) images for tumor detection in situ. Examination of tumor distributions from the surface of the colon to deeper inside is essential for determining a treatment plan of cancer. For example, the submucosal invasion depth of tumors in addition to the tumor distributions on the colon surface is used as an indicator of whether the endoscopic dissection would be operated. Thus, we devised the FL multimodal endoscopic system to offer information on the tumor distribution from the surface to deep tissue with high accuracy. This system was evaluated with bilayer gelatin phantoms which have different properties at each layer of the phantom in a lateral direction. After evaluating the system with phantoms, it was employed to characterize forty human colon tissues excised from cancer patients. The proposed system could allow us to obtain highly resolved chemical, anatomical, and macro-molecular information on excised colon tissues including tumors, thus enhancing the detection of tumor distributions from the surface to deep tissue. These results suggest that the FL multimodal endoscopic system could be an innovative screening instrument for quantitative tumor characterization.