Samsung Electronics Co., Ltd.

Saifeng Ni

Boon Loong Ng

Madhukar Budagavi

Vutha Va

Anum Ali

Priyabrata Parida

Rajan Laxman Joshi

Indranil Sinharoy

Xiaohu Guo

Zhipeng Fan

Ran Luo

An apparatus includes a communication interface configured to receive a bitstream for a compressed video and a processor operably coupled to the communication interface. The processor is configured to decode the bitstream for the compressed video and obtain reference samples associated with a block of a video frame. The processor is also configured to determine an interpolation filter type for use in obtaining predicted samples. The processor is also configured to select an interpolation filter of the interpolation filter type based on a block size of the block of the video frame. The processor is also configured to apply the interpolation filter to the reference samples. The processor is also configured to output one or more predicted samples using the interpolated reference samples.

Block-based reference sample interpolation filter optimization for video

An electronic device includes a transceiver configured to transmit and receive radar signals and a processor operatively coupled to the transceiver. The processor is configured to identify, based on the received radar signals, a plurality of radar frames related to an activity of a target. The processor is further configured to extract a plurality of features from the plurality of radar frames, compute burst attributes for the extracted features, predict a gesture based on the burst attributes, determine whether the predicted gesture is a valid gesture, and if the predicted gesture is a valid gesture, perform an action corresponding to the predicted gesture.

Burst-based non-gesture rejection in a micro-gesture recognition system

A method includes obtaining a gesture sample via a gesture classifier. The gesture sample includes parameters of features extracted from the radar signals based on user motion in performance of a gesture. The method includes determining whether to obtain feedback for a target gesture associated with the gesture sample. The method includes in response to a determination to obtain the feedback, obtaining the feedback for the target gesture. The feedback includes a label indicating a type of gesture. The method includes determining whether the gesture sample associated with the label is valid based on comparison to a dataset of pre-existing validated gesture samples and a distance threshold. The method includes in response to determining that the gesture sample associated with the label is valid, determining whether to update a model for the gesture classifier using the validated gesture sample as a training sample.

Robustifying radar-based gesture recognition solution using contextual information

An apparatus for three dimensional (3D) art viewing includes one or more sensors and a processor operably coupled to the one or more sensors. The processor is configured to detect, using the one or more sensors, a position of a user. The processor is additionally configured to output, for display, an aspect of an image based on the position of the user. The processor is also configured to obtain, using the one or more sensors, movement data associated with a movement of the user. The processor is further configured to apply temporal smoothing to smooth the movement data. In addition, the processor is configured to map the smoothed movement data to a series of view indices. The processor is also configured to change the aspect of the image for display based on the mapped series of view indices.

3D arts viewing on display devices

An electronic device for object rigging includes a processor. The processor is configured to obtain a three-dimensional (3D) scan of an object. The processor is also configured to identify 3D coordinates associated with joints of the 3D scan. The processor is further configured to identify parameters associated with fitting a 3D parametric body model to the 3D scan based on the 3D coordinates of the joints. Additionally, the processor is configured to modify the parameters to reduce 3D joint errors between the 3D coordinates associated with the joints on the 3D scan and the 3D parametric body model. The processor is also configured to generate a rigged 3D scan based on the modified parameters, for performing an animated motion.

Body shape and pose estimation via volumetric regressor for raw three dimensional scan models

An electronic device for object rigging includes a processor. The processor is configured to obtain a 3D scan of an object. The processor is also configured to match a rigged parametric model to the 3D scan by minimizing a surface distance and 3D joint errors between the rigged parametric model and the 3D scan. The processor is further configured to identify a correspondence between the rigged parametric model and the 3D scan. Additionally, the processor is configured to transfer attributes of the rigged parametric model to the 3D scan based on the correspondence to generate a rigged 3D scan. The processor is also configured to apply animation motion to the rigged 3D scan. The rigged 3D scan with the applied animation motion is rendered on a display.

Growing community of inventors

Milpitas, CA, United States of America

Saifeng Ni