A device and method of object detection in a scene by combining traditional 2D visual light imaging such as pixels with 3D data such as a voxel map are described. A single lens directs image light from the scene to a dichroic mirror which then provides light to a both a 2D visible light image sensor and a 3D sensor, such as a time-of-flight sensor that uses a transmitted, modulated IR light beam, which is then synchronously demodulated to determine time of flight as well as 2D coordinates. 2D portions (non-distance) of 3D voxel image data are aligned with the 2D pixel image data such that each is responsive to the same portion of the scene. Embodiments determine true reflectivity, true scale, and image occlusion. 2D images may be enhanced by the 3D true reflectivity. Combined data may be used as training data for object detection and recognition.

An apparatus comprising a memory to store a first image captured by a first camera and a second image captured by a second camera; and a processor comprising circuitry, the processor to identify viewpoint information defining a view for a stitched image, the stitched image to be generated from a combination of a plurality of images comprising the first image and the second image; and based on the viewpoint information and a projection type, determine transformation parameters for at least one reference region associated with overlapping regions of the first image and the second image in order to: localize overlapping regions of the first image and the second image to determine stitching parameters; combine the first image and the second image using the stitching parameters; and assign data of the combined first image and the second image to the stitched image.

The present invention relates to a deep-learning based system and method of automatically determining a degree of damage to each area of a vehicle, which is capable of quickly calculating a consistent and reliable quote for vehicle repair by analyzing an image of a vehicle in an accident by using a deep learning-based Mark R-CNN framework and then extracting a component image corresponding to a damaged part, and automatically determining the degree of damage in the extracted component image based on a pre-trained model.

Systems, methods, and articles of manufacture are disclosed that enable the compression of depth data and real-time reconstruction of high-quality light fields. In one aspect, spatial compression and decompression of depth images is divided into the following stages: generating a quadtree data structure for each depth image captured by a light field probe and difference mask associated with the depth image, with each node of the quadtree approximating a corresponding portion of the depth image data using an approximating function; generating, from the quadtree for each depth image, a runtime packed form that is more lightweight and has a desired maximum error; and assembling multiple such runtime packed forms into per-probe stream(s); and decoding at runtime the assembled per-probe stream(s). Further, a block compression format is disclosed for approximating depth data by augmenting the block compression format 3DC+(BC4) with a line and two pairs of endpoints.

An image recognition method and apparatus. The method comprises: obtaining original image data, convolutional neural network configuration parameters, and convolutional neural network operation parameters from a data transfer bus, the original image data comprising M pieces of pixel data, and M being a positive integer (101); and performing convolutional neural network operation on the original image data by a convolutional neural network operation module according to the convolutional neural network configuration parameters and the convolutional neural network operation parameters (102), wherein the convolutional neural network operation module comprises a convolution operation unit, a batch processing operation unit, and an activation operation unit connected in sequence. The method improves the real timeliness of image recognition.

Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

In some embodiments, a memory controller in a processor includes a base value cache, a compressor, and a metadata cache. The compressor is coupled to the base value cache and the metadata cache. The compressor compresses a data block using at least a base value and delta values. The compressor determines whether the size of the data block exceeds a data block threshold value. Based on the determination of whether the size of the compressed data block generated by the compressor exceeds the data block threshold value, the memory controller transfers only a set of the compressed delta values to memory for storage. A decompressor located in the lower level cache of the processor decompresses the compressed data block using the base value stored in the base value cache, metadata stored in the metadata cache and the delta values stored in memory.

In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a visual computing device over a network. The processor is to: access visual data captured by a camera; detect a particular feature in the visual data, wherein the particular feature comprises a visual indication of privacy-sensitive information; sanitize the visual data to mask the privacy-sensitive information associated with the particular feature, wherein sanitizing the visual data causes sanitized visual data to be produced; and transmit, via the communication interface, the sanitized visual data to the visual computing device over the network, wherein the visual computing device is to use the sanitized visual data to process a visual query associated with the visual data.

An image reading apparatus includes a reading unit configured to read an image of a document and generate image data, a filtering unit configured to perform filtering processing on the image data generated by the reading unit and generate image data, a binarization unit configured to perform binarization processing based on the image data generated by the filtering unit using a first threshold value to generate first binary image data, and perform binarization processing based on the image data generated by the filtering unit using a second threshold value to generate second binary image data, and a detection unit configured to detect an edge in the image data generated by the reading unit based on the first binary image data and the second binary image data generated by the binarization unit.

Described herein are systems and techniques for generating training data for use in training a machine learning model for image enhancement. The system may access a target image of a displayed video frame, wherein the target image represents a target output of the machine learning model. The system may access an input image of the displayed video frame, wherein the input image corresponds to the target image and represents an input to the machine learning model. The system may train the machine learning model using the target image and the input image corresponding to the target image to obtain a trained machine learning model.