Abstract: An encoding device sets a region of interest corresponding to an input image, and prepares, as an intermediate image, data in which the input image is associated with region-of-interest information, designates an embedding position, embeds the region-of-interest information in a pixel value form into the intermediate image in accordance with the embedding position, prepares, as a region-of-interest setting image, data associated with the region-of-interest information, encodes the image by using a predetermined image coding scheme, and outputs an encoded image. A decoding device analyzes a decoded image obtained through decoding, reads the region-of-interest information, prepares, as a region-of-interest information read image, data in which the decoded image is associated with the region-of-interest information, applies a post-filter on the basis of the region-of-interest information read image, and outputs a post-filtered image.

Abstract: A method of video decoding at a decoder is disclosed. The method can include receiving a current block in a picture, and determining whether a size of the current block is smaller than or equal to a size threshold. When the size of the current block is smaller than or equal to the size threshold, one or more types of sub-block based merge candidates for decoding the current block can be disabled.

Abstract: Systems and methods are disclosed for generating a latent space residual. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining a target frame, obtaining a reconstructed frame, encoding the target frame into a latent space to generate a latent space target frame, encoding the reconstructed frame into the latent space to generate a latent space reconstructed frame, and generating a latent space residual based on the latent space target frame and the latent space reconstructed frame.

Abstract: A lightweight, portable and configurable system for image acquisition for photogrammetry purposes includes a portable rig having at least two cameras supported thereon in spaced relation to one another. The cameras are angled towards one another and actuated in an automated fashion so as to capture images of an object at a minimum rate over time. At least a plurality of the captured images are used to digitally reconstruct three-dimensional geometry of the object.

Abstract: An image encoding device includes an encoding circuit configured to encode an image, the image being constituted of a plurality of columns and a plurality of rows of which width are longer than the columns, generate a reference image and stores the reference image into a memory, and output a bit stream including the encoded image. The image encoding device also includes an image rotation circuit configured to rotate the image read from the memory by 90° and output the rotated image to a encoding processing circuit, and a read address generating circuit configured to read the column of the image from the memory, and provide the column with the image rotation circuit.

Abstract: The present invention provides a method for a finalized processed image and related data to identify a spatial location of each pupil in the region. Each pupil is identified by a two-dimensional spatial coordinate. The method includes processing information associated with each pupil identified by the two-dimensional spatial coordinate to output a plurality of two-dimensional spatial coordinates, each of which is in reference to a time, in a two-dimensional space. The method then includes outputting a gaze information about the human user. The gaze information includes the two-dimensional spatial coordinates each of which is in reference to a time in a two-dimensional space.

Abstract: A technique for sharing a peripheral device among a group of systems comprises capturing a set of images of a user, and processing the set of images of the user to determine a user directive to designate a first system in the group as an owner of a peripheral device of a second system in the group. If the peripheral device is an input device, the technique further comprises redirecting, responsive to the user directive, from the second system to the first system, data entered using the input device of the second system. If the peripheral device is an output device, the technique further comprises forwarding, responsive to the user directive, from the first system to the second system, data for processing by the output device of the second system. In an embodiment, the user directive is in the form of the user's eye gaze directed at a camera.

Abstract: Systems and methods are disclosed for reconstructing a frame. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining one or more reference frames from non-transient electronic storage, generating one or more displacement maps based on the one or more reference frames and a target frame with the physical computer processor, generating one or more warped frames based on the one or more reference frames and the one or more displacement maps with the physical computer processor, obtaining a conditioned reconstruction model from the non-transient electronic storage, and generating one or more blending coefficients and one or more reconstructed displacement maps by applying the one or more displacement maps, the one or more warped frames, and a target frame to the conditioned reconstruction model with the physical computer processor.

Abstract: An input video stream of video content may be encoded and transmitted from a provider to an intermediary, which decodes and edits the video content, and then re-encodes and transmits the video content to end viewers via an output video stream. When re-encoding the video content, the intermediary may determine to selectively re-use and/or not re-use input motion vectors from the input video stream, for example based on an amount of distortion associated with editing of the video content. In some examples, input motion vectors may be re-used for re-encoding of certain portions (e.g., frames, parts of frames, etc.) of the output video stream and not re-used for re-encoding of other portions of the output video stream.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes receiving circuitry and processing circuitry. For example, the processing circuitry decodes prediction information of a current block in a picture from a coded video bitstream, and determines, based on an intra block copy (IBC) prediction mode usage flag from the decoded prediction information, an IBC prediction mode that is separate from an inter prediction mode and an intra prediction mode. Further, the processing circuitry determines, a block vector that points to a reference area in the picture in response to the determination of the IBC prediction mode, and reconstructs the current block based on reference samples within the reference area in the picture.

Abstract: According to the present invention, a video decoding method comprises the steps of: deriving two motion vectors (MVs) for a current block; determining a super sample from among samples in the current block; deriving a refined motion vector and a first refined prediction sample for the super sample on the basis of the two MVs; deriving a second refined prediction sample for a nonsuper sample on the basis of the refined motion vector, wherein the non-super sample is a sample that is not the super sample from among the samples; and generating reconstructed samples on the basis of the first refined prediction sample and the second refined prediction sample. According to the present invention, a more accurate refined motion vector in a sample unit of a current block can be derived, and inter prediction efficiency can be significantly improved.

Abstract: A video data stream is rendered reducible in a manner so that the reduction leads to a restriction of pictures of the reduced video data stream to merely a predetermined subarea of the pictures of the original video data stream and in a manner so that transcoding, such as re-quantization, may be avoided and a conformance of the reduced video data stream relative to the codec underlying the original video data stream be maintained. This is achieved by providing the video data stream with information including an indication of the predetermined subarea and replacement indices for redirecting the indices included by the payload portion so as to refer to, and/or replacement parameters for adjusting the first set of coding parameter settings so as to result in, a second set of coding parameter settings.

Abstract: A method, system, and article of efficient illuminator and camera sensor synchronization to capture images comprises generating a sequence of frames each associated with a captured image and comprising operating an electronic shutter using vertical-blanks (vblanks) occurring between the last reset of a previous frame and a first read of a current frame consecutively after the previous frame of the sequence of frames. The generating also comprises receiving, by at least one camera sensor, from at least one infra-red-related illuminator and limited to a time within or equal to the vblanks so that the illuminator is turned on and off at the same vblank, and sensing the received light at the camera sensor to convert the light into image data to form the frames in the sequence of frames.

Abstract: A method comprising receiving control instructions sent from a control device, where the control instructions are configured to instruct a photographing apparatus carried by an unmanned aerial vehicle to perform an image capturing operation; and controlling an indicator light at the unmanned aerial vehicle to indicate an execution status of the control instructions executed by the photographing apparatus.

Abstract: A system for detecting electronic components includes a light-source device, a photography device, an adjustment device, and an image-processing device. The light-source device generates a light to illuminate at least one pin of a first electronic component at different rotation angles. The photography device senses the light and generates first and second images corresponding to the pin of the first electronic component at different rotation angles. The adjustment device adjusts the photography device and the light-source device to a first height and a second height, wherein the first images correspond to the first height and the second images correspond to the second height. The image-processing device calculates first feature information of the pin of the first electronic component according the first and second images, and analyzes the state of the pin of the first electronic component according to the first feature information.

Abstract: A method for using an alternate frame reference (ARF) includes selecting an anchor frame and video frames, where the anchor frame includes an anchor block, and the anchor block includes an anchor pixel; identifying, for the anchor block of the anchor frame, respective reference blocks in the video frames; determining, for the anchor pixel and using an anchor patch, respective distances between the anchor pixel and respective co-located reference pixels of the respective reference blocks, where the anchor patch includes anchor patch pixels, and a respective distance, of the respective distances, between the anchor pixel and a respective co-located reference pixel is determined using the anchor patch pixels and co-located reference pixels; determining, using the respective distances, respective weights; determining, using the respective weights, an ARF pixel that is co-located with the anchor pixel; and encoding, in a compressed bitstream, the ARF.

Abstract: Speeding up small block intra-prediction in video coding is described herein. The system includes an encoder. The encoder is to execute intra-prediction by deriving a plurality of prediction angles, wherein the prediction angles are based on a video coding standard. The encoder is also to disable a prediction angle for a current block to eliminate a dependency on an immediate predecessor block.

Abstract: A method for controlling a movable object includes receiving a user input indicative of a command to adjust a perception of a target while tracking the target, determining a subsequent perception of the target based on the user input, and generating one or more control signals to move the movable object based on the subsequent perception of the target.

Abstract: A refrigerator (1) is provided with an image capturing camera 18 (image capturing unit) configured to capture an image of an interior of a storage chamber (such as a refrigeration chamber 3); and a communication portion (52) (communication unit) configured to transmit image of the interior of the storage chamber captured by the image capturing camera (18) to an external device.

Abstract: An observation device includes: a structured illumination section; a phase difference measurement illumination section; a phase contrast lens that has a phase plate for dimming illumination light for phase difference measurement, where the illumination light for phase difference measurement is incident into the lens, and the structured illumination light is incident into the lens from a side opposite to an incidence side of the ring-shaped illumination; a detection section that detects reflected light of the structured illumination light; and an observation section that images the illumination light for phase difference measurement. When Fourier transform is performed on the structured illumination light, a spatial frequency of the structured illumination light is set on a high-frequency side or a low-frequency side with respect to a position of the phase plate on optical Fourier space.