Abstract: A method and device are disclosed for estimating an interaction with the device. The method includes configuring a first token and a second token of an estimation model according to first features of a 3D object, applying a first weight to the first token to produce a first-weighted input token and applying a second weight that is different from the first weight to the second token to produce a second-weighted input token, and generating, by a first encoder layer of an estimation-model encoder of the estimation model, an output token based on the first-weighted input token and the second-weighted input token. The method may include receiving, at a 2D feature extraction model, the first features from a backbone, extracting, by the 2D feature extraction model, second features including 2D features, and receiving, at the estimation-model encoder, data generated based on the 2D features.

Abstract: A method and apparatus are provided. The method includes generating a dataset for real-world super resolution (SR), training a first generative adversarial network (GAN), training a second GAN, and fusing an output of the first GAN and an output of the second GAN.

Abstract: A system and a method that provide video semantic segmentation are disclosed herein. A first frame of a sequence of video frames is semantically segmented to obtain at least one first semantic feature of the first frame. A second frame of the sequence is semantically segmented to obtain at least one second semantic feature of the second frame in which the second frame is subsequent to the first frame. A third frame of the sequence is semantically segmented to obtain at least one third semantic feature in which the third frame is subsequent to the second frame and also being subsequent to the first frame by a first predetermined number of consecutive frames. The at least one first semantic feature, the at least one second semantic feature and the at least one third semantic feature are combined to form at least one fourth semantic feature for the second frame.

Abstract: A method includes: computing noise data by subtracting, by a processing circuit, a noisy image from a corresponding ground truth image; clustering, by the processing circuit, a plurality of noise values of the noise data based on intensity values of the corresponding ground truth image; permuting, by the processing circuit, a plurality of locations of the noise values of the noise data within each cluster; generating, by the processing circuit, a synthetic noise image based on the permuted locations of the noise values; adding, by the processing circuit, the synthetic noise image to the corresponding ground truth image to generate a synthetic noisy image; and augmenting an image dataset for training a neural network to perform image denoising with the synthetic noisy image.

Abstract: Embodiments of this application provide an image transmission method and apparatus.

Abstract: A method and an apparatus are provided for performing visual inertial odometry (VIO). Measurements are processed from an inertial measurement unit (IMU), a camera, and a depth sensor. Keyframe residue including at least depth residue is determined based on the processed measurements. A sliding window graph is generated and optimized based on factors derived from the keyframe residue. An object pose is estimated based on the optimized sliding window graph.

Abstract: A method of performing scene-dependent lens shading correction (SD-LSC) is provided. The method includes collecting scene information from a Bayer thumbnail of an input image; generating a standard red green blue (sRGB) thumbnail by processing the Bayer thumbnail of the input image to simulate white balance (WB) and pre-gamma blocks; determining a representative color channel ratio of the input image based on the scene information and the sRGB thumbnail; determining an ideal grid gain of the input image based on the representative color channel ratio and a grid gain of the input image; merging the ideal grid gain and the grid gain of the input image to generate a new grid gain; and applying the new grid gain to the input image.

Abstract: A method for denoising an image includes: receiving, by a processing circuit of a user equipment, an input image; supplying, by the processing circuit, the input image to a trained convolutional neural network (CNN) including a multi-scale residual dense block (MRDB), the MRDB including: a residual dense block (RDB); and an atrous spatial pyramid pooling (ASPP) module; computing, by the processing circuit, an MRDB output feature map using the MRDB; and computing, by the processing circuit, an output image based on the MRDB output feature map, the output image being a denoised version of the input image.

Abstract: A method and an apparatus are provided for providing a dolly zoom effect by an electronic device. A first image with a first depth map and a second image with a second depth map are obtained. A first synthesized image and a corresponding first synthesized depth map are generated using the first image and the first depth map respectively. A second synthesized image and a corresponding second synthesized depth map are generated using the second image and the second depth map respectively. A fused image is generated from the first synthesized image and the second synthesized image. A fused depth map is generated from the first synthesized depth map and the second synthesized depth map. A final synthesized image is generated based on processing the fused image and the fused depth map.

Abstract: An electronic device and method for texturing a three dimensional (3D) model are provided. The method includes rendering a texture atlas to obtain a first set of two dimensional (2D) images of the 3D model; rendering a ground truth texture atlas to obtain a second set of 2D images of the 3D model; comparing the first set of images with the second set of images to determine a rendering loss; applying the texture sampling properties to a convolutional neural network (CNN) to incorporate the rendering loss into a deep learning framework; and inputting a 2D texture atlas into the CNN to generate a texture of the 3D module.

Abstract: A method and apparatus are provided. The method includes generating a dataset for real-world super resolution (SR), training a first generative adversarial network (GAN), training a second GAN, and fusing an output of the first GAN and an output of the second GAN.

Abstract: A method for denoising an image includes: receiving, by a processing circuit of a user equipment, an input image; supplying, by the processing circuit, the input image to a trained convolutional neural network (CNN) including a multi-scale residual dense block (MRDB), the MRDB including: a residual dense block (RDB); and an atrous spatial pyramid pooling (ASPP) module; computing, by the processing circuit, an MRDB output feature map using the MRDB; and computing, by the processing circuit, an output image based on the MRDB output feature map, the output image being a denoised version of the input image.

Abstract: An apparatus and method for determining image sharpness is provided. According to one embodiment, an apparatus includes a weight device configured to determine a weight map of a reference image; an image sharpening device configured to sharpen the reference image using at least one sharpening method; an edge activity map device connected to the image sharpening device and configured to determine a first edge activity map ?(x, y) for each sharpened image of reference image by the at least one sharpening method; and an edge sharpness metric device connected to the weight device and the first edge activity map device and configured to determine an edge sharpness metric (ESM) for each sharpened image of the reference image by the at least one sharpening method based on the weight map and the edge activity map for each sharpened image of the reference image by the at least one sharpening method.

Abstract: A method and an apparatus are provided for providing a dolly zoom effect by an electronic device. A first image with a first depth map and a second image with a second depth map are obtained. A first synthesized image and a corresponding first synthesized depth map are generated using the first image and the first depth map respectively. A second synthesized image and a corresponding second synthesized depth map are generated using the second image and the second depth map respectively. A fused image is generated from the first synthesized image and the second synthesized image. A fused depth map is generated from the first synthesized depth map and the second synthesized depth map. A final synthesized image is generated based on processing the fused image and the fused depth map.

Abstract: A method and an apparatus are provided for sharpening an image, by an image processor of an electronic device. An input image is received. Low pass filtering is applied to the input image to generate a first image and a second image. A kernel size of first image and the second image are different. Edge preserving filtering is applied to the input image to generate a third image and a fourth image. A kernel size of the third image and the fourth image are different. The first image is subtracted from the third image to obtain a first resulting image. The first image has a larger kernel size than the third image. The second image from the fourth image to obtain a second resulting image. The second image has a larger kernel size than the fourth image. The first resultant image, the second resultant image, and the input image are summed to generate a sharpened image.

Abstract: A method and an apparatus are provided for sharpening an image, by an image processor of an electronic device. An input image is received. Low pass filtering is applied to the input image to generate a first image and a second image. A kernel size of first image and the second image are different. Edge preserving filtering is applied to the input image to generate a third image and a fourth image. A kernel size of the third image and the fourth image are different. The first image is subtracted from the third image to obtain a first resulting image. The first image has a larger kernel size than the third image. The second image from the fourth image to obtain a second resulting image. The second image has a larger kernel size than the fourth image.

Abstract: An apparatus and method for determining image sharpness is provided. According to one embodiment, an apparatus includes a weight device configured to determine a weight map of a reference image; an image sharpening device configured to sharpen the reference image using at least one sharpening method; an edge activity map device connected to the image sharpening device and configured to determine a first edge activity map ?(x, y) for each sharpened image of reference image by the at least one sharpening method; and an edge sharpness metric device connected to the weight device and the first edge activity map device and configured to determine an edge sharpness metric (ESM) for each sharpened image of the reference image by the at least one sharpening method based on the weight map and the edge activity map for each sharpened image of the reference image by the at least one sharpening method.

Abstract: An interference cancellation (IC) processor, a method, a method of manufacturing a semiconductor device, and a method of constructing an integrated circuit are provided. The IC processor includes a plurality of mono interference cancellation (MIC) filter estimation processors; a combined effective channel calculation processor; a combined filter calculation processor; and a combined filter processor, including a first input connected to the output of the combined filter calculation processor, a second input for receiving a signal for setting a length of the combined filter that is connected to a second input of the IC processor, a third input connected to the input of the MIC-BRC processor, and an output for providing a filtered output of a de-rotated GMSK signal that is connected to a second output of the IC processor that provides a filtered output yi of the de-rotated GMSK signal.

Abstract: An interference cancellation (IC) processor, a method, a method of manufacturing a semiconductor device, and a method of constructing an integrated circuit are provided. The IC processor includes a plurality of mono interference cancellation (MIC) filter estimation processors; a combined effective channel calculation processor; a combined filter calculation processor; and a combined filter processor, including a first input connected to the output of the combined filter calculation processor, a second input for receiving a signal for setting a length of the combined filter that is connected to a second input of the IC processor, a third input connected to the input of the MIC-BRC processor, and an output for providing a filtered output of a de-rotated GMSK signal that is connected to a second output of the IC processor that provides a filtered output yi of the de-rotated GMSK signal.

Abstract: A method and apparatus for measuring power in an electronic device is provided. A voltage is sensed across a sense resistor and the current is then calculated by dividing the sensed voltage by the value of the sense resistor. The method incorporates a buffer for storing the sensed voltage and calculated current. In addition, the buffer permits the measurements to be taken while the electronic device is in a sleep state. The measurements that may be taken include voltage, current, and power.