Abstract: Techniques for generating style-transferred images are provided. In some embodiments, a content image, a style image, and a user input indicating one or more modifications that operate on style-transferred images are received. In some embodiments, an initial style-transferred image is generated using a machine learning model. In some examples, the initial style-transferred image comprises features associated with the style image applied to content included in the content image. In some embodiments, a modified style-transferred image is generated by modifying the initial style-transferred image based at least in part on the user input indicating the one or more modifications.

Abstract: The present disclosure provides a bioprinter nozzle, a bioprinter and a lumen tissue construct printing method. The bioprinter nozzle includes: a bio-ink flow channel disposed inside the bioprinter nozzle; a bio-ink ejection port in communication with the bio-ink flow channel and located on the lateral side of an ejection end of the bioprinter nozzle; a medical adhesive flow channel disposed inside the bioprinter nozzle and isolated from the bio-ink flow channel; and a medical adhesive ejection port in communication with the medical adhesive flow channel and disposed on the lateral side of the ejection end, the medical adhesive ejection port and the bio-ink ejection port being arranged in a staggered manner in the axial direction of the bioprinter nozzle. The bioprinter includes the bioprinter nozzle. The lumen tissue construct printing method uses the bioprinter for printing.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images via multi-resolution generator neural networks. The disclosed system extracts multi-resolution features from a scene representation to condition a spatial feature tensor and a latent code to modulate an output of a generator neural network. For example, the disclosed systems utilizes a base encoder of the generator neural network to generate a feature set from a semantic label map of a scene. The disclosed system then utilizes a bottom-up encoder to extract multi-resolution features and generate a latent code from the feature set. Furthermore, the disclosed system determines a spatial feature tensor by utilizing a top-down encoder to up-sample and aggregate the multi-resolution features. The disclosed system then utilizes a decoder to generate a synthesized digital image based on the spatial feature tensor and the latent code.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images using class-specific generators for objects of different classes. The disclosed system modifies a synthesized digital image by utilizing a plurality of class-specific generator neural networks to generate a plurality of synthesized objects according to object classes identified in the synthesized digital image. The disclosed system determines object classes in the synthesized digital image such as via a semantic label map corresponding to the synthesized digital image. The disclosed system selects class-specific generator neural networks corresponding to the classes of objects in the synthesized digital image. The disclosed system also generates a plurality of synthesized objects utilizing the class-specific generator neural networks based on contextual data associated with the identified objects.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly restoring degraded digital images utilizing a deep learning framework for repairing local defects, correcting global imperfections, and/or enhancing depicted faces. In particular, the disclosed systems can utilize a defect detection neural network to generate a segmentation map indicating locations of local defects within a digital image. In addition, the disclosed systems can utilize an inpainting algorithm to determine pixels for inpainting the local defects to reduce their appearance. In some embodiments, the disclosed systems utilize a global correction neural network to determine and repair global imperfections. Further, the disclosed systems can enhance one or more faces depicted within a digital image utilizing a face enhancement neural network as well.

Abstract: The present disclosure relates to systems, computer-implemented methods, and non-transitory computer readable medium for automatically transferring makeup from a reference face image to a target face image using a neural network trained using semi-supervised learning. For example, the disclosed systems can receive, at a neural network, a target face image and a reference face image, where the target face image is selected by a user via a graphical user interface (GUI) and the reference face image has makeup. The systems transfer, by the neural network, the makeup from the reference face image to the target face image, where the neural network is trained to transfer the makeup from the reference face image to the target face image using semi-supervised learning. The systems output for display the makeup on the target face image.

Abstract: A polymer-based spherical powder preparation device and preparation process are disclosed. The preparation device comprises a mill milling system and an inductively coupled plasma powder spheroidization system. The mill milling system of the preparation device can achieve ultra-fine grinding of the material at room temperature by applying strong extrusion, shear and circumferential stress to the material; and the inductively coupled plasma powder spheroidization system using high temperature plasma as high temperature heat source, the polymer powder can be heated uniformly, and the melting and cooling rate is fast, so the spheroidization can be completed in a short time. The preparation process of polymer based spherical powder was integrated and continuously produced by the preparation device.

Abstract: The present disclosure provides a bioprinter spray head assembly and a bioprinter, wherein the spray head assembly is internally provided with a first flow channel and a second flow channel, an outlet of the first flow channel is adjacent to an outlet of the second flow channel, and the outlet of the second flow channel is configured to make a second material sprayed therefrom move towards a first material out of the outlet of the first flow channel, such that the second material sprayed from the outlet of the second flow channel and the first material sprayed from the outlet of the first flow channel are combined together to form a fluid printing unit. The bioprinter spray head assembly can guide the auxiliary materials to wrap the cells for protection, thereby reducing the cell damage caused by the extrusion pressure and the frictional force subjected in the printing process, so as to improve the survival rate of the cells and present a high reliability.

Abstract: A cached information updating method includes receiving an update request, determining an update processing manner according to a number of pieces of cached information to be updated indicated in the update request, and updating the cached information according to the update processing manner, to update differently according to different numbers of pieces of cached information.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize image-guided model inversion of an image classifier with a discriminator. The disclosed systems utilize a neural network image classifier to encode features of an initial image and a target image. The disclosed system also reduces a feature distance between the features of the initial image and the features of the target image at a plurality of layers of the neural network image classifier by utilizing a feature distance regularizer. Additionally, the disclosed system reduces a patch difference between image patches of the initial image and image patches of the target image by utilizing a patch-based discriminator with a patch consistency regularizer. The disclosed system then generates a synthesized digital image based on the constrained feature set and constrained image patches of the initial image.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently modifying a generative adversarial neural network using few-shot adaptation to generate digital images corresponding to a target domain while maintaining diversity of a source domain and realism of the target domain. In particular, the disclosed systems utilize a generative adversarial neural network with parameters learned from a large source domain. The disclosed systems preserve relative similarities and differences between digital images in the source domain using a cross-domain distance consistency loss. In addition, the disclosed systems utilize an anchor-based strategy to encourage different levels or measures of realism over digital images generated from latent vectors in different regions of a latent space.

Abstract: This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that utilize channel pruning and knowledge distillation to generate a compact noise-to-image GAN. For example, the disclosed systems prune less informative channels via outgoing channel weights of the GAN. In some implementations, the disclosed systems further utilize content-aware pruning by utilizing a differentiable loss between an image generated by the GAN and a modified version of the image to identify sensitive channels within the GAN during channel pruning. In some embodiments, the disclosed systems utilize knowledge distillation to learn parameters for the pruned GAN to mimic a full-size GAN.

Abstract: Technologies for image processing based on a creation workflow for creating a type of images are provided. Both multi-stage image generation as well as multi-stage image editing of an existing image are supported. To accomplish this, one system models the sequential creation stages of the creation workflow. In the backward direction, inference networks can backward transform an image into various intermediate stages. In the forward direction, generation networks can forward transform an earlier-stage image into a later-stage image based on stage-specific operations. Advantageously, this technical solution overcomes the limitations of the single-stage generation strategy with a multi-stage framework to model different types of variation at various creation stages. Resultantly, both novices and seasoned artists can use these technologies to efficiently perform complex artwork creation or editing tasks.

Abstract: The present disclosure relates to a device for printing a lumen tissue construct, a method for using the same, and a 3D bioprinter. The device includes a spray head assembly for printing a biological construct; and a bioprinting platform for supporting a lumen tissue, and for carrying a biological construct printed by the spray head assembly, and for applying the biological construct to an inner surface of the lumen tissue. The device for printing a lumen tissue construct of the present disclosure provides the spray head assembly and the bioprinting platform, and the spray head assembly applies the biological construct onto the inner surface of the lumen tissue by the bioprinting platform, to avoid such problems as recurrence of thrombus and restenosis of a lumen after the lumen tissue has been implanted for a long time, thereby improving the biological reliability of the lumen tissue.

Abstract: One example method involves operations for receiving a request to transform an input image into a target image. Operations further include providing the input image to a machine learning model trained to adapt images. Training the machine learning model includes accessing training data having a source domain of images and a target domain of images with a target style. Training further includes using a pre-trained generative model to generate an adapted source domain of adapted images having the target style. The adapted source domain is generated by determining a rate of change for parameters of the target style, generating weighted parameters by applying a weight to each of the parameters based on their respective rate of change, and applying the weighted parameters to the source domain. Additionally, operations include using the machine learning model to generate the target image by modifying parameters of the input image using the target style.

Abstract: The present disclosure provides a vector graphics data processing method, system, medium, and vector graphics processing device. The method includes the following operations: building a vector primitive path intersection data structure (PIDS) based on coordinates of path intersections (PIs); when a new PI is generated, comparing information of the new PI to information of existing PIs corresponding to an X coordinate or Y coordinate of the new PI; and storing the information of the new PI at a corresponding position in the PIDS corresponding to the X coordinate or Y coordinate of the new PI based on a result of the comparing. Only effective PI data are saved, thereby reducing memory footprint and memory bandwidth, and improving vector graphics processing performance.

Abstract: The present invention relates to the technical field of a bioprinter, and in particular relates to a bioprinter temperature control system and a bioprinter. The bioprinter temperature control system provided by the present invention, comprises a flow channel temperature control system, for controlling a temperature of a flow channel between an outlet of a bioprinting material container of a bioprinter and a nozzle of the bioprinter, such that the temperature of the flow channel conforms to a desired temperature of a biological printing material. The temperature control system of the present invention can realize the temperature control of the biological printing material, improving the survival rate of the printing material, and ensuring the biological function of the printing material.

Abstract: An expansion anchor includes an anchor bolt and an expansion sleeve which surrounds the anchor bolt. The expansion sleeve has an expansion tongue and an anchor tongue and the anchor bolt has a backward-pointing expansion slope for radially displacing the expansion tongue and a backward-pointing anchor slope for radially displacing the anchor tongue. The backward-pointing anchor slope extends more steeply than the backward-pointing expansion slope at least in some regions.

Abstract: The present disclosure relates to a bioprinter spray head assembly and a bioprinter, wherein the bioprinter spray head assembly comprises an outer nozzle having a second channel and an inner nozzle having a first channel, the inner nozzle is coaxially provided within the second channel, the first channel forms a first material channel, and an annular space between the outer nozzle and the inner nozzle forms a second material channel, which surrounds the first material channel at an outlet of the first material channel, for converging a second material sprayed from an outlet of the second material channel toward a first material sprayed from the outlet of the first material channel, so as to form a fluid printing unit.

Abstract: The present disclosure relates to systems, computer-implemented methods, and non-transitory computer readable medium for automatically transferring makeup from a reference face image to a target face image using a neural network trained using semi-supervised learning. For example, the disclosed systems can receive, at a neural network, a target face image and a reference face image, where the target face image is selected by a user via a graphical user interface (GUI) and the reference face image has makeup. The systems transfer, by the neural network, the makeup from the reference face image to the target face image, where the neural network is trained to transfer the makeup from the reference face image to the target face image using semi-supervised learning. The systems output for display the makeup on the target face image.