Abstract: In various examples, systems and methods are disclosed relating to generating an output 3D latent representation by encoding, using a text encoder, a text prompt and encoding, using a 2D-3D encoder, a 2D image of an object or a 3D representation of the object. A 3D output is generated by applying the output 3D latent representation to a decoder. A reconstruction loss and a SDS loss are determined for the 3D output. At least one of the text encoder, the 2D-3D encoder, and the decoder is updated using the reconstruction loss and the SDS loss.

Abstract: In various examples, images (e.g., novel views) of an object may be rendered using an optimized number of samples of a 3D representation of the object. The optimized number of the samples may be determined based at least on casting rays into a scene that includes the 3D representation of the object and/or an acceleration data structure corresponding to the object. The acceleration data structure may include features corresponding to characteristics of the object, and the features may be indicative of the number of samples to be obtained from various portions of the 3D representation of the object to render the images. In some examples, the 3D representation may be a neural radiance field that includes, as a neural output, a spatially varying kernel size predicting the characteristics of the object, and the features of the acceleration data structure may be related to the spatially varying kernel size.

Abstract: Apparatuses, systems, and techniques to generate a two-dimensional (2D) image. In at least one embodiment, one or more neural networks are used to generate the image and a three-dimensional (3D) mesh representation of the image, wherein the 3D mesh representation is to be used to apply one or more effects to the 2D image.

Abstract: A multi-sensor fusion method and system for intelligent driving vehicles are provided, which relate to the technical field of intelligent driving vehicles. The method includes: establishing an extended target tracker based on a GM-PHD algorithm and a rectangular target model of a detected object; processing detection information of a millimeter-wave radar by using the extended target tracker to obtain millimeter-wave radar track information of the detected object; processing detection information of a laser radar by using the established bounding-box detector and a JPDA tracker provided with an IMM-UKF to obtain laser-radar track information of the detected object; processing the millimeter-wave radar track information and the laser-radar track information by performing time-space conversion to obtain a central fusion node; and processing the central fusion node by using an IMF algorithm to obtain global track information.

Abstract: The present disclosure involves methods, apparatus, and systems for predicting performance of a content delivery network (CDN). An example method includes determining a topology of a content delivery network (CDN); determining a first proxy node to test; testing the first proxy node at a test data rate to determine a first tested capacity of the first proxy node by: distributing the test data rate across intermediate nodes connected to the first proxy node; determining the first tested capacity of the first proxy node based on whether a total available capacity of edge nodes exceeds a distributed test data rate at the intermediate node; determining a second proxy node to test; testing the second proxy node to determine a second tested capacity of the second proxy node; and determining a capacity of the graph model based on the first tested capacity and the second tested capacity.

Abstract: A method for positioning a terminal device using an apparatus is provided. The method comprises: performing a first positioning of the terminal device based on WiFi angle estimation received from the terminal device: rotating a mmW antenna array to a target direction based on the first positioning: transmitting a radar signal via the rotated mmW antenna array; and performing a second positioning of the terminal device based on an echo received from the terminal device.

Abstract: Apparatuses, systems, and techniques to train one or more neural networks using stratified sampled training data parameters. In at least one embodiment, one or more stochastic training data parameters may be stratified sampled from one or more sampling ranges to compute a gradient for updating the one or more neural networks.

Abstract: In one embodiment, a method includes accessing a plurality of images of a region of interest of a person's skin and extracting, from the plurality of images, a color signal of the region of interest as a function of time. The method further includes determining, based at least on the color signal, a first quality associated with an estimated vital sign of the person, where the vital sign estimate is determined from the plurality of images.

Abstract: Systems and methods are disclosed related to a 3D grounded video foundation model. A video generation method and system provide 3D conditioning information to a video diffusion model to improve generated video quality (object and temporal consistency) that is grounded in three dimensions (3D). The video generation method and system also enable precise camera control, cinematic effects, and scene editing. Video output corresponding to a set of camera specifications is generated for a scene from input image(s) including one or more images of a static scene or a sequence of images (video) for a dynamic scene. The input image(s) are used to calculate a 3D cache representing the scene. The 3D cache is rendered according to the set of camera specifications to produce a frame sequence and a mask sequence that identifies missing pixels in each frame. The frame sequence is encoded and masked to generate the output video.

Abstract: Systems and methods are disclosed related to a 3D grounded video foundation model. A video generation method and system provide 3D conditioning information to a video diffusion model to improve generated video quality (object and temporal consistency) that is grounded in three dimensions (3D). The video generation method and system also enable precise camera control, cinematic effects, and scene editing. Video output corresponding to a set of camera specifications is generated for a scene from input image(s) including one or more images of a static scene or a sequence of images (video) for a dynamic scene. The input image(s) are used to calculate a 3D cache representing the scene. The 3D cache is rendered according to the set of camera specifications to produce a frame sequence and a mask sequence that identifies missing pixels in each frame. The frame sequence is encoded and masked to generate the output video.

Abstract: Approaches are presented for training an inverse graphics network. An image synthesis network can generate training data for an inverse graphics network. In turn, the inverse graphics network can teach the synthesis network about the physical three-dimensional (3D) controls. Such an approach can provide for accurate 3D reconstruction of objects from 2D images using the trained inverse graphics network, while requiring little annotation of the provided training data. Such an approach can extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers, enabling a disentangled generative model to function as a controllable 3D “neural renderer,” complementing traditional graphics renderers.

Abstract: Various embodiments described herein relate to providing a force sensing apparatus with stress-concentration sections for sensing forces associated with a vehicle braking system. In this regard, a force sensing apparatus includes a metal elastomer element, a set of sensing elements, and a circuit board element. The metal elastomer element includes a set of stress-concentration sections formed on a surface of the metal elastomer element. The set of sensing elements are disposed on the set of stress-concentration sections. The circuit board element includes a shape associated with the surface of the metal elastomer element. The set of sensing elements are configured to detect a brake force based on one or more deformations associated with the set of stress-concentration sections formed on the surface of the metal elastomer element. The set of sensing elements are further configured to transform the brake force into one or more electrical signals.

Abstract: Provided herein are liposomes comprising B-cell lymphoma (Bcl) protein inhibitors, compositions comprising such liposomes, and methods using such formulations for treating hyperproliferative disorders.

Abstract: Text-to-image generation generally refers to the process of generating an image from one or more text prompts input by a user. While artificial intelligence has been a valuable tool for text-to-image generation, current artificial intelligence-based solutions are more limited as it relates to text-to-3D content creation. For example, these solutions are oftentimes category-dependent, or synthesize 3D content at a low resolution. The present disclosure provides a process and architecture for high-resolution text-to-3D content creation.

Abstract: A real-time location system comprises sensors and an upstream device communicating with the sensors. Sensor pairs of the sensors include a transmitting sensor and a receiving sensor. Each sensor is assigned as the transmitting sensor in turn, while all other sensors are designated as the receiving sensors and collect signal strength data. The upstream device determines a labelled dataset based on the signal strength data for the sensor pairs and zone labels associated with the signal strength data. The RTLS ML model is trained based on the labelled dataset.

Abstract: Approaches presented herein provide systems and methods to reuse a rendered image for noising and denoising steps used for training one or more content generation systems. The reused rendered image may reduce computationally expensive processes, such as content generation and rendering, and enable multiple gradients to be compared using a common image that may be noised and then processed by one or more diffusion models to compute a gradient. The gradients may be combined and used to retrain the model, providing more training data with less variance between generating and rendering steps.

Abstract: Apparatuses, systems, and techniques to generate a a two-dimensional (2D) image. In at least one embodiment, one or more neural networks are used to generate the image and a three-dimensional (3D) mesh representation of the image, wherein the 3D mesh representation is to be used to apply one or more effects to the 2D image.

Abstract: In various examples, systems and methods are disclosed relating to generating an output 3D latent representation by encoding, using a text encoder, a text prompt and encoding, using a 2D/3D encoder, a 2D image of an object or a 3D representation of the object. A 3D output is generated by applying the output 3D latent representation to a decoder. A reconstruction loss and a SDS loss are determined for the 3D output. At least one of the text encoder, the 2D/3D encoder, and the decoder is updated using the reconstruction loss and the SDS loss.

Abstract: Systems and methods are disclosed relating to reservoir characterization. A computed tomography (CT) imaging device is used to generate a CT image of a rock sample from a reservoir and segmented into CT slices. The CT slices are processed to identify textures of the rock sample to provide texture data. The rock sample is scanned using nuclear magnetic resonance (NMR) to provide NMR data. The NMR data is segmented to provide NMR segments. The NMR segments and texture data are analyzed to determine a contribution of each texture in each CT slice to one or more relaxation times in a corresponding NMR segment for each CT slice. A petrophysical property is predicted for each texture of each CT slice based on a contribution of each texture and the corresponding NMR segment for each CT slice. A petrophysical model for the reservoir is generated based on the predicted petrophysical property.