Abstract: A computing system and method can be used to render a 3D shape from one or more images. In particular, the present disclosure provides a general pipeline for learning articulated shape reconstruction from images (LASR). The pipeline can reconstruct rigid or nonrigid 3D shapes. In particular, the pipeline can automatically decompose non-rigidly deforming shapes into rigid motions near rigid-bones. This pipeline incorporates an analysis-by-synthesis strategy and forward-renders silhouette, optical flow, and color images which can be compared against the video observations to adjust the internal parameters of the model. By inverting a rendering pipeline and incorporating optical flow, the pipeline can recover a mesh of a 3D model from the one or more images input by a user.

Abstract: Example aspects of the present disclosure are directed to systems and methods which feature a machine-learned video super-resolution (VSR) model which has been trained using a bi-directional training approach. In particular, the present disclosure provides a compression-informed (e.g., compression-aware) super-resolution model that can perform well on real-world videos with different levels of compression. Specifically, example models described herein can include three modules to robustly restore the missing information caused by video compression. First, a bi-directional recurrent module can be used to reduce the accumulated warping error from the random locations of the intra-frame from compressed video frames. Second, a detail-aware flow estimation module can be added to enable recovery of high resolution (HR) flow from compressed low resolution (LR) frames. Finally, a Laplacian enhancement module can add high-frequency information to the warped HR frames washed out by video encoding.

Abstract: Systems and methods of the present disclosure are directed to a computing system. The computing system can obtain a message vector and video data comprising a plurality of video frames. The computing system can process the input video with a transformation portion of a machine-learned watermark encoding model to obtain a three-dimensional feature encoding of the input video. The computing system can process the three-dimensional feature encoding of the input video and the message vector with an embedding portion of the machine-learned watermark encoding model to obtain spatial-temporal watermark encoding data descriptive of the message vector. The computing system can generate encoded video data comprising a plurality of encoded video frames, wherein at least one of the plurality of encoded video frames includes the spatial-temporal watermark encoding data.

Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

Abstract: A wireless charging apparatus includes a receive end coil, a switch selection circuit, a plurality of charging circuits, and a receive end controller. An input end of the switch selection circuit is connected to an output end of the receive end coil, and an output end of the switch selection circuit is connected to an input end of each of the charging circuits.

Abstract: Example aspects of the present disclosure are directed to systems and methods which feature a machine-learned video super-resolution (VSR) model which has been trained using a bi-directional training approach. In particular, the present disclosure provides a compression-informed (e.g., compression-aware) super-resolution model that can perform well on real-world videos with different levels of compression. Specifically, example models described herein can include three modules to robustly restore the missing information caused by video compression. First, a bi-directional recurrent module can be used to reduce the accumulated warping error from the random locations of the intra-frame from compressed video frames. Second, a detail-aware flow estimation module can be added to enable recovery of high resolution (HR) flow from compressed low resolution (LR) frames. Finally, a Laplacian enhancement module can add high-frequency information to the warped HR frames washed out by video encoding.

Abstract: A battery protection apparatus power protection apparatus is configured to protect an electrochemical cell connected to a load, and includes a protection IC, a switching transistor group, and a sampling resistor. The protection IC includes two power input terminals respectively connected to positive and negative electrodes of the electrochemical cell, and an operational amplifier, where the operational amplifier includes a positive input pin, a negative input pin, and an output pin. The switching transistor group is connected between the negative electrode of the electrochemical cell and the load, and is configured to control turn-on and turn-off of a charge and discharge circuit of the electrochemical cell. The sampling detection resistor Rs is serially connected between the sampling circuit detection terminal and the output pin, where the main circuit detection terminal is connected to the positive input pin, and the sampling circuit detection terminal is connected to the negative input pin.

Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

Abstract: Methods, systems, and computer programs encoded on a computer storage medium, that relate to extracting digital watermarks from images, irrespective of distortions introduced into these images. Methods can include inputting a first data item into a channel encoder that can generate a first encoded data item that is greater in length than the first data item and that (1) includes the input data item and (2) new data this is redundant of the input data item. Based on the first encoded data item and a first image, an encoder model can generate a first encoded image into which the first encoded data is embedded as a digital watermark. A decoder model can decode the first encoded data item to generate a second data, which can be decoded by the channel decoder to generate data that is predicted to be the first data.

Abstract: A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.

Abstract: A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating realistic extensions of images. In one aspect, a method comprises providing an input that comprises a provided image to a generative neural network having a plurality of generative neural network parameters. The generative neural network processes the input in accordance with trained values of the plurality of generative neural network parameters to generate an extended image. The extended image has (i) more rows, more columns, or both than the provided image, and (ii) is predicted to be a realistic extension of the provided image. The generative neural network is trained using an adversarial loss objective function.

Abstract: Methods, systems, and computer programs encoded on a computer storage medium, that relate to extracting digital watermarks from images, irrespective of distortions introduced into these images. Methods can include inputting a first data item into a channel encoder that can generate a first encoded data item that is greater in length than the first data item and that (1) includes the input data item and (2) new data this is redundant of the input data item. Based on the first encoded data item and a first image, an encoder model can generate a first encoded image into which the first encoded data is embedded as a digital watermark. A decoder model can decode the first encoded data item to generate a second data, which can be decoded by the channel decoder to generate data that is predicted to be the first data.

Abstract: A multimedia communication system and computer-implemented method for transmitting auxiliary display content to an end-user communication device to be rendered on a display device with a special effect to emphasize an image included in the auxiliary display content, comprising analyzing image data included in an auxiliary display content to detect an object image or a background image, determining a special effect based on the analysis of the image data, applying the special effect to the auxiliary display content to modify display properties for the auxiliary display content such that the object image is emphasized or pops out, and sending the auxiliary display content with modified display properties to the end-user communication device. The special effect can comprise a non-customization special effect, a simple foreground special effect or a selective foreground special effect.

Abstract: Example batteries, terminals, and charging systems are described. One example battery includes a battery charging port, a battery discharging port, a battery negative port, an overcurrent protection element, a protection integrated circuit, a control switch, and an electrochemical cell. The battery charging port is connected to a positive electrode of the electrochemical cell. The control switch is connected in series between a negative electrode of the electrochemical cell and the battery negative port. The protection integrated circuit is connected in parallel to two ends of the electrochemical cell. The protection integrated circuit is further connected to the control switch so as to send a control signal to the control switch. In addition, the overcurrent protection element is connected in series between the battery discharging port and the positive electrode of the electrochemical cell. The battery provided in the present application has both a charging path and a discharging path.

Abstract: A multimedia communication system and computer-implemented method for transmitting auxiliary display content to an end-user communication device to be rendered on a display device with a special effect to emphasize an image included in the auxiliary display content, comprising a processor and a transmitter. The processor can be arranged to analyze image data included in an auxiliary display content, detect an object image or a background image in the auxiliary display content based on the analysis of the image data, determine a special effect based on the analysis of the image data, and apply the special effect to the auxiliary display content to modify display properties for the auxiliary display content such that the object image is emphasized or pops-out. The transmitter can be arranged to send the auxiliary display content with modified display properties to an end-user communication device.

Abstract: A terminal and a fast charging method includes sending, by the terminal, instruction information to a charger connected to the terminal in order to instruct the charger to adjust an output voltage and an output current; converting, by the terminal, the output voltage of the charger into 1/K times the output voltage; and converting the output current of the charger into K times the output current such that a charging circuit between two sides of a battery charges the battery with the 1/K times the output voltage and the K times the output current, where K is a conversion coefficient of a conversion circuit with a fixed conversion ratio in the terminal and is a constant value, and K is any real number greater than one.

Abstract: A method includes determining, based on an image having an initial viewpoint, a depth image, and determining a foreground visibility map including visibility values that are inversely proportional to a depth gradient of the depth image. The method also includes determining, based on the depth image, a background disocclusion mask indicating a likelihood that pixel of the image will be disoccluded by a viewpoint adjustment. The method additionally includes generating, based on the image, the depth image, and the background disocclusion mask, an inpainted image and an inpainted depth image. The method further includes generating, based on the depth image and the inpainted depth image, respectively, a first three-dimensional (3D) representation of the image and a second 3D representation of the inpainted image, and generating a modified image having an adjusted viewpoint by combining the first and second 3D representation based on the foreground visibility map.

Abstract: A terminal and a fast charging method to fast charge the terminal, where the method includes: sending, by the terminal, instruction information to a charger connected to the terminal in order to instruct the charger to adjust an output voltage and an output current; converting, by the terminal, the output voltage of the charger into 1/K times the output voltage; and converting the output current of the charger into K times the output current such that a charging circuit between two sides of a battery charges the battery with the 1/K times the output voltage and the K times the output current, where K is a conversion coefficient of a conversion circuit with a fixed conversion ratio in the terminal and is a constant value, and K is any real number greater than one.

Abstract: A method includes obtaining a reference image and a target image each representing an environment containing moving features and static features. The method also includes determining an object mask configured to mask out the moving features and preserves the static features in the target image. The method additionally includes determining, based on motion parallax between the reference image and the target image, a static depth image representing depth values of the static features in the target image. The method further includes generating, by way of a machine learning model, a dynamic depth image representing depth values of both the static features and the moving features in the target image. The model is trained to generate the dynamic depth image by determining depth values of at least the moving features based on the target image, the object mask, and the static depth image.