Abstract: Systems and methods for estimating depths of features in a scene or environment surrounding a user of a spatial computing system, such as a virtual reality, augmented reality or mixed reality (collectively, cross reality) system, in an end-to-end process. The estimated depths can be utilized by a spatial computing system, for example, to provide an accurate and effective 3D cross reality experience.

Abstract: Techniques are generally described for fusing sensor data of different modalities using a transformer. In various examples, first sensor data may be received from a first sensor and second sensor data may be received from a second sensor. A first feature representation of the first sensor data may be generated using a first machine learning model and a second feature representation of the second sensor data may be generated using a second machine learning model. In some examples, a modified first feature representation of the first sensor data may be generated based at least in part on a self-attention mechanism of a transformer encoder. The modified first feature representation may be generated based at least in part on the first feature representation and the second feature representation. A computer vision task may be performed using the modified first feature representation.

Abstract: A neural network in multi-task deep learning paradigm for machine vision includes an encoder that further includes a first, a second, and a third tier. The first tier comprises a first-tier unit having one or more first-unit blocks. The second tier receives a first-tier output from the first tier at one or more second-tier units in the second tier, a second-tier unit comprises one or more second-tier blocks, the third tier receives a second-tier output from the second tier at one or more third-tier units in the third tier, and a third-tier block comprises one or more third-tier blocks. The neural network further comprises a decoder operatively the encoder to receive an encoder output from the encoder as well as one or more loss function layers that are configured to backpropagate one or more losses for training at least the encoder of the neural network in a deep learning paradigm.

Abstract: A method using a two-dimensional (2D) image representation of three-dimensional (3D) geometric objects in a machine learning framework has been developed. The method includes generating a single 2D geometry image corresponding to a 3D object model, and providing the single geometry image as input to a shape analysis task to enable shape analysis of the 3D object model based only on information encoded in the single 2D geometry image in the machine learning framework.

Abstract: A method using a two-dimensional (2D) image representation of three-dimensional (3D) geometric objects in a machine learning framework has been developed. The method includes generating a single 2D geometry image corresponding to a 3D object model, and providing the single geometry image as input to a shape analysis task to enable shape analysis of the 3D object model based only on information encoded in the single 2D geometry image in the machine learning framework.

Abstract: Systems and methods for estimating depths of features in a scene or environment surrounding a user of a spatial computing system, such as a virtual reality, augmented reality or mixed reality (collectively, cross reality) system, in an end-to-end process. The estimated depths can be utilized by a spatial computing system, for example, to provide an accurate and effective 3D cross reality experience.

Abstract: Systems and methods for gradient adversarial training of a neural network are disclosed. In one aspect of gradient adversarial training, an auxiliary neural network can be trained to classify a gradient tensor that is evaluated during backpropagation in a main neural network that provides a desired task output. The main neural network can serve as an adversary to the auxiliary network in addition to a standard task-based training procedure. The auxiliary neural network can pass an adversarial gradient signal back to the main neural network, which can use this signal to regularize the weight tensors in the main neural network. Gradient adversarial training of the neural network can provide improved gradient tensors in the main network. Gradient adversarial techniques can be used to train multitask networks, knowledge distillation networks, and adversarial defense networks.

Abstract: A neural network in multi-task deep learning paradigm for machine vision includes an encoder that further includes a first, a second, and a third tier. The first tier comprises a first-tier unit having one or more first-unit blocks. The second tier receives a first-tier output from the first tier at one or more second-tier units in the second tier, a second-tier unit comprises one or more second-tier blocks, the third tier receives a second-tier output from the second tier at one or more third-tier units in the third tier, and a third-tier block comprises one or more third-tier blocks. The neural network further comprises a decoder operatively the encoder to receive an encoder output from the encoder as well as one or more loss function layers that are configured to backpropagate one or more losses for training at least the encoder of the neural network in a deep learning paradigm.