Diffusion-based technologies have made significant strides, particularly in personalized and customized facial generation. However, existing methods struggle to achieve high-fidelity and detailed identity (ID) consistency. This is mainly due to two challenges: insufficient fine-grained control over specific facial areas and the absence of a comprehensive strategy for ID preservation that accounts for both intricate facial details and the overall facial structure. To address these limitations, we introduce ConsistentID, an innovative method crafted for diverse identity-preserving portrait generation under fine-grained multimodal facial prompts, utilizing only a single reference image. ConsistentID comprises two core components: a multimodal facial prompt generator and an ID-preservation network. The facial prompt generator combines localized facial features, facial feature descriptions, and overall facial descriptions to enhance the precision of facial detail reconstruction. The ID-preservation network, optimized with a facial attention localization strategy, ensures consistent identity preservation across facial regions. Together, these components leverage fine-grained multimodal identity information to improve identity preservation accuracy significantly. To drive ConsistentID’s training, we propose a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets. Experimental results substantiate that our ConsistentID achieves exceptional precision and diversity in personalized facial generation, surpassing existing methods in the MyStyle dataset. In addition, although ConsistentID introduces more multimodal ID information, it still maintains rapid inference speed during the generation process.

Selection of the best quality embryo is the key for a faithful implantation in in vitro fertilization (IVF) practice. However, the process of evaluating numerous images captured by time‐lapse imaging (TLI) system is time‐consuming and some important features cannot be recognized by naked eyes. Convolutional neural network (CNN) is used in medical imaging yet in IVF. The study aims to apply CNN on day‐one human embryo TLI. We first presented CNN algorithm for day‐one human embryo segmentation on three distinct features: zona pellucida (ZP), cytoplasm and pronucleus (PN). We tested the CNN performance compared side‐by‐side with manual labelling by clinical embryologist, then measured the segmented day‐one human embryo parameters and compared them with literature reported values. The precisions of segmentation were that cytoplasm over 97%, PN over 84% and ZP around 80%. For the morphometrics data of cytoplasm, ZP and PN, the results were comparable with those reported in literatures, which showed high reproducibility and consistency. The CNN system provides fast and stable analytical outcome to improve work efficiency in IVF setting. To conclude, our CNN system is potential to be applied in practice for day‐one human embryo segmentation as a robust tool with high precision, reproducibility and speed.

Sketch recognition relies on two types of information, namely, spatial contexts like the local structures in images and temporal contexts like the orders of strokes. Existing methods usually adopt convolutional neural networks (CNNs) to model spatial contexts, and recurrent neural networks (RNNs) for temporal contexts. However, most of them combine spatial and temporal features with late fusion or single-stage transformation, which is prone to losing the informative details in sketches. To tackle this problem, we propose a novel framework that aims at the multi-stage interactions and refinements of spatial and temporal features. Specifically, given a sketch represented by a stroke array, we first generate a temporal-enriched image (TEI), which is a pseudo-color image retaining the temporal order of strokes, to overcome the difficulty of CNNs in leveraging temporal information. We then construct a dual-branch network, in which a CNN branch and a RNN branch are adopted to process the stroke array and the TEI respectively. In the early stages of our network, considering the limited ability of RNNs in capturing spatial structures, we utilize multiple enhancement modules to enhance the stroke features with the TEI features. While in the last stage of our network, we propose a spatio-temporal enhancement module that refines stroke features and TEI features in a joint feature space. Furthermore, a bidirectional temporal-compatible unit that adaptively merges features in opposite temporal orders, is proposed to help RNNs tackle abrupt strokes. Comprehensive experimental results on QuickDraw and TU-Berlin demonstrate that the proposed method is a robust and efficient solution for sketch recognition.

In the field of robotic hand design, soft body and anthropomorphic design are two trends with a promising future. Designing soft body anthropomorphic robotic hands with human-like grasping ability, but with a simple and reliable structure, is a challenge that still has not been not fully solved. In this paper, we present an anatomically correct robotic hand 3D model that aims to realize the human hand’s functionality using a single type of 3D-printable material. Our robotic hand 3D model is combined with bones, ligaments, tendons, pulley systems, and tissue. We also describe the fabrication method to rapidly produce our robotic hand in 3D printing, wherein all parts are made by elastic 50 A (shore durometer) resin. In the experimental section, we show that our robotic hand has a similar motion range to a human hand with substantial grasping strength and compare it with the latest other designs of anthropomorphic robotic hands. Our new design greatly reduces the fabrication cost and assembly time. Compared with other robotic hand designs, we think our robotic hand may induce a new approach to the design and production of robotic hands as well as other related mechanical structures.

Most current anthropomorphicrobotic hands can realize part of the human hand functions, particularly for object grasping. However, due to the complexity of the human hand, few current designs target at daily object manipulations, even for simple actions like rotating a pen. To tackle this problem, we introduce a gesture based framework, which adopts the widely-used 33 grasping gestures of Feix as the bases for hand design and implementation of manipulation. In the proposed framework, we first measure the motion ranges of human fingers for each gesture, and based on the results, we propose a simple yet dexterous robotic hand design with 13 degrees of actuation. Furthermore, we adopt a frame interpolation based method, in which we consider the base gestures as the key frames to represent a manipulation task, and use the simple linear interpolation strategy to accomplish the manipulation. To demonstrate the effectiveness of our framework, we define a three-level benchmark, which includes not only 62 test gestures from previous research, but also multiple complex and continuous actions. Experimental results on this benchmark validate the dexterity of the proposed design and our video is available in https://drive.google.com/file/d/1wPtkd2P0zolYSBW7_3tVMUHrZEeXLXgD/view?usp=sharing.

Current research of designing prosthetic robotic hands mainly focuses on improving their functionality by devising new mechanical structures and actuation systems. Most of existing work relies on a single structure/system (e.g., bone-only or tissue-only) and ignores the fact that the human hand is composed of multiple functional structures (e.g., skin, bones, muscles, and tendons). This may increase the difficulty of the design process and lower the flexibility of the fabricated hand. To tackle this problem, this paper proposes a three-dimensional (3D) printable multi-layer design that models the hand with the layers of skin, tissues, and bones. The proposed design first obtains the 3D surface model of a target hand via 3D scanning, and then generates the 3D bone models from the surface model based on a fast template matching method. To overcome the disadvantage of the rigid bone layer in deformation, the tissue layer is introduced and represented by a concentric tubebased structure, of which the deformability can be explicitly controlled by a parameter. The experimental results show that the proposed design outperforms previous designs remarkably. With the proposed design, prosthetic robotic hands can be produced quickly with low cost and be customizable and deformable.