Abstract: Techniques are described for compressing and decompressing data using machine learning systems. An example process can include receiving a plurality of images for compression by a neural network compression system. The process can include determining, based on a first image from the plurality of images, a first plurality of weight values associated with a first model of the neural network compression system. The process can include generating a first bitstream comprising a compressed version of the first plurality of weight values. The process can include outputting the first bitstream for transmission to a receiver.

Abstract: Techniques for facilitating light signal assessment receiver systems and methods are provided. In one example, a light signal assessment device includes a light signal detection device including a filter array, a detector array, and a measurement device. The filter array is configured to filter a light signal incident on the filter array. The detector array is configured to receive the filtered light signal and generate a light signal detection image based on the filtered light signal. The measurement device is configured to determine a characteristic associated with the light signal based on the light signal detection image. The assessment device further includes a logic device configured to generate an output based on the characteristic. Related methods and systems are also provided.

Abstract: The present invention concerns a method of encapsulating subpicture bitstreams in at least one media file, the subpicture bitstreams corresponding to encoded media data of a subpicture corresponding to a rectangular region of video data, the method comprising: obtaining the plurality of subpicture bitstreams; encapsulating each subpicture bitstream in a subpicture track; generating at least one base track referencing at least two subpicture tracks and forming a spatial arrangement of the at least two subpicture tracks; generating information describing APS referenced by samples of the at least two subpicture tracks; encapsulating the subpicture tracks, the at least one base track and the information describing APS in the at least one media file.

Abstract: An electronic apparatus and method are disclosed herein. The electronic device includes at least one camera, a distance sensor, an illumination sensor, a display, a light-emitting module configured to generate a flash, and a processor. The processor implements the method, including: displaying a camera preview image, acquiring a distance between the apparatus and an object depicted in the preview image, acquiring a brightness in the local environment, detecting whether a shadow of the electronic apparatus is depicted in the preview image, based on the acquired distance and the acquired brightness, detecting whether a shadow is disposed within the field-of-view of the camera, and in response to detecting the shadow of, configuring a brightness value for a flash to reduce the shadow.

Abstract: A camera with a field of view toward an external environment of an aircraft is disposed within an aircraft door such that an engine inlet of an engine of the aircraft is within the field of view of the camera. A display device is disposed within an interior of the aircraft. A processor is operatively coupled to the camera and to the display device. The processor analyzes image data captured by the camera to determine whether persons or foreign objects are present near the engine inlet, or detect damage or deformation of the engine inlet.

Abstract: A coding apparatus is a coding apparatus for coding an original image and includes: a division section that divides the original image into blocks that are a plurality of areas to acquire the plurality of blocks; a determination section that, for each of the blocks, determines whether or not to determine the block as an interpolation target; and a substitution section that substitutes a value of a pixel included in the block determined as the interpolation target, with a value that decreases a code amount of the block determined as the interpolation target. The determination section determines whether or not to determine the area that is a target of the determination as an area that is the interpolation target, using an evaluation based on an accuracy of prediction of an image of the block by intra prediction or inter prediction and a degree of the area that is the interpolation target being a generated one.

Abstract: Decoding and/or encoding video information included in a bitstream can involve a predicted quantization matrix associated with at least a portion of the video information and a syntax element indicating that at least one coefficient of the predicted quantization matrix is to be interpreted as a residual such that the decoding and/or encoding of at least a portion of the video information is based on a combination of the predicted quantization matrix and the residual, where the syntax element is obtained from the bitstream during decoding, or included in the bitstream during encoding.

Abstract: A computer-implemented method for contrastive object representation from temporal data using an artificial neural network (ANN) includes receiving, by the ANN, a video. The video comprises a temporal sequence of frames including images of one or more objects. The ANN generates object representations corresponding to the one or more objects based on temporal data of multiple frames of the temporal sequence of frames. The object representations are communicated to a receiver.

Abstract: In various examples, machine learning of encoding parameter values for a network is performed using a video encoder. Feedback associated with streaming video encoded by a video encoder over a network may be applied to an MLM(s). Using such feedback, the MLM(s) may predict a value(s) of an encoding parameter(s). The video encoder may then use the value to encode subsequent video data for the streaming. By using the video encoder in training, the MLM(s) may learn based on actual encoded parameter values of the video encoder. The MLM(s) may be trained via reinforcement learning based on video encoded by the video encoder. A rewards metric(s) may be used to train the MLM(s) using data generated or applied to the physical network in which the MLM(s) is to be deployed and/or a simulation thereof. Penalty metric(s) (e.g., the quantity of dropped frames) may also be used to train the MLM(s).

Abstract: A measuring device according to the present technology includes a light emitting unit configured to emit light to a fluid, a light receiving unit configured to perform photoelectric conversion for incident light using an electron avalanche phenomenon by a plurality of pixels to obtain a light reception signal, and a control unit configured to perform processing of detecting a target object in the fluid on the basis of the light reception signal and execute an imaging operation of the target object on condition that the target object is detected.

Abstract: An image encoding/decoding method and apparatus are provided. An image decoding method according to the present disclosure may include: obtaining palette information and palette index prediction information of a current block from a bitstream; constructing a palette predictor for the current block based on the palette information and constructing a palette table for the current block based on the palette predictor; generating a palette index map for the current block based on the palette index prediction information; and decoding the current block based on the palette table and the palette index map, wherein the palette predictor may be initialized using a user defined palette entry obtained from at least one of an adaptation parameter set (APS), a picture parameter set (PPS) or a slice header.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media for an unmanned aerial vehicle (UAV) wind turbine inspection system. One of the methods includes obtaining first sensor information by an unmanned aerial vehicle (UAV), the first sensor information describing physical aspects of a wind turbine, including one or more blades of the wind turbine. An orientation of the blades of the wind turbine are determined based on the obtained first sensor information. A flight pattern for the UAV to inspect the blades of the wind turbine is determined, the flight pattern being based on the determined orientation of the blades. Each of the blades of the wind turbine is inspected by the UAV according to the determined flight pattern, the inspection including obtaining second sensor information describing the blades of the wind turbine.

Abstract: An information processing apparatus includes: a processor in communication with a memory configured to store instructions that, when executed by the processor, cause the processor to set a label based on element information included in scene information for a scene, and determine, based on the set label, whether or not to store the scene information set with the label.

Abstract: A control apparatus for controlling an imaging apparatus includes a determination unit configured to determine whether at least one subject in an image captured by the imaging apparatus is an authenticated subject, and a control unit configured to, in a case where the determination unit determines that the at least one subject is not an authenticated subject, control exposure of the image by targeting the at least one subject.

Abstract: The present specification discloses a method of decoding an image. The method includes obtaining a motion vector of a collocated block included in a reference picture of a current block in a temporal motion buffer; changing a format of the obtained motion vector; and deriving the motion vector, in which the format is changed, into a temporal motion vector of the current block.

Abstract: A method of video decoding includes determining, for a current block of a picture, one of a plurality of reference lines. The method includes determining an intra prediction mode for the current block in accordance with the determined one of the plurality of reference lines. The method further includes performing intra prediction for the current block based on the determined intra prediction mode and one or more samples included in the determined one of the plurality of reference lines. The plurality of reference lines includes an adjacent reference line that is adjacent to the current block and at least one non-adjacent reference line that is not adjacent to the current block, and each of the at least one non-adjacent reference line is associated with a decreasing number of intra prediction modes with respect to a direction away from the current block.

Abstract: A video signal decoding device comprising a processor, wherein the processor is configured to: obtain reference samples corresponding to a first side of a current block and reference samples corresponding to a second side of the current block, obtain a direct current (DC) value for prediction of the current block based on a reference sample set comprising at least some of the reference samples corresponding to the first side and the reference samples corresponding to the second side, and reconstruct the current block based on the DC value.

Abstract: A method for decoding a video according to the present invention may comprise: determining a first prediction mode for a first sub-block in a current block and a second intra prediction mode for a second sub-block, performing a first prediction for the first sub-block based on the first intra prediction mode, performing a second prediction for the second sub-block based on the second intra prediction mode, and obtaining a prediction sample of the current block according to a result of the first prediction and the second prediction.

Abstract: Methods, systems, and apparatuses for adaptive processing of video content to remove noise, such as film grain noise, without substantially affecting visual presentation quality are described herein. A computing device may determine a plurality of film grain parameters associated with film grain noise present within one or more portions of a content item. The computing device may determine at least one encoding parameter based on the plurality of film grain parameters. The computing device may encode the content item based on the at least one encoding parameter. The computing device may send an encoding message to at least one user device/client device, which may in turn use the encoding message to decode the content item.

Abstract: According to one implementation, an image compression system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an input image, transform the input image to a latent space representation of the input image, and quantize the latent space representation of the input image to produce multiple quantized latents. The hardware processor further executes the software code to encode the quantized latents using a probability density function of the latent space representation of the input image, to generate a bitstream, and convert the bitstream into an output image corresponding to the input image. The probability density function of the latent space representation of the input image is obtained based on a normalizing flow mapping of one of the input image or the latent space representation of the input image.