Apparatus and methods for providing software and hardware based solutions to the problem of synthesizing noise for a digital image. According to one aspect, a probability image is generated and noise blocks are randomly placed at locations in the probability image where the locations have probability values that are compared to a threshold criterion, creating a synthesized noise image. Embodiments include generating synthesized film grain images and synthesized digital camera noise images.

A point cloud data encoding method and decoding method, a device, a medium, and a program product are provided, and relate to the field of point cloud application technologies. One method includes obtaining point cloud data, the point cloud data comprising at least two data points; and sequentially encoding data points in the point cloud data according to encoding orders of the data points, to obtain encoded point cloud data corresponding to the point cloud data, wherein the encoding orders of the data points being determined based on distances among the data points. Another method includes obtaining encoded point cloud data, obtaining reference information, the reference information being used for indicating a start reference data point of an encoding queue; and sequentially decoding, based on the reference information and the encoded point cloud data, data points according to the encoding orders of the data points.

A computer apparatus and methods generate multi-parametric color composite images from multi-echo chemical shift encoded (CSE) MRI. Some embodiments use inherently co-registered images (i.e., image maps) that are combined into a single intuitive composite color image. The color (e.g., brightness, hue, and/or saturation) reflects in part the water and fat content, and other properties, particularly T2* relaxation (related to magnetic susceptibility) of the tissue.

A computer apparatus and methods generate multi-parametric color composite images from multi-echo chemical shift encoded (CSE) MRI. Some embodiments use inherently co-registered images (i.e., image maps) that are combined into a single intuitive composite color image. The color (e.g., brightness, hue, and/or saturation) reflects in part the water and fat content, and other properties, particularly T2* relaxation (related to magnetic susceptibility) of the tissue.

Embodiments of the present disclosure discloses a scene-aware video encoder system. The scene-aware encoder system transforms a sequence of video frames of a video of a scene into a spatio-temporal scene graph. The spatio-temporal scene graph includes nodes representing one or multiple static and dynamic objects in the scene. Each node of the spatio-temporal scene graph describes an appearance, a location, and/or a motion of each of the objects (static and dynamic objects) at different time instances. The nodes of the spatio-temporal scene graph are embedded into a latent space using a spatio-temporal transformer encoding different combinations of different nodes of the spatio-temporal scene graph corresponding to different spatio-temporal volumes of the scene. Each node of the different nodes encoded in each of the combinations is weighted with an attention score determined as a function of similarities of spatio-temporal locations of the different nodes in the combination.

A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

A method, computer program, and computer system is provided for point cloud coding. Data corresponding to a point cloud is received. Hash elements corresponding to attribute values associated with the received data is reconstructed. A size of a hash table may be decreased based on deleting one or more of the hash elements corresponding to non-border regions associated with the attribute values. The data corresponding to the point cloud is decoded based on the reconstructed hash elements.

A method of interframe point cloud attribute coding is performed by at least one processor and includes coding a first color attribute of a point of a point cloud to obtain a first reconstructed residual, coding a second color attribute of the point to obtain a second reconstructed residual, and determining a quantization index of the second reconstructed residual, based on the first reconstructed residual and the second reconstructed residual. The method further includes updating the second reconstructed residual, based on the quantization index and the first reconstructed residual.

A method of interframe point cloud attribute coding is performed by at least one processor and includes coding a first color attribute of a point of a point cloud to obtain a first reconstructed residual, coding a second color attribute of the point to obtain a second reconstructed residual, and determining a quantization index of the second reconstructed residual, based on the first reconstructed residual and the second reconstructed residual. The method further includes updating the second reconstructed residual, based on the quantization index and the first reconstructed residual.

Technologies for providing shared memory for accelerator sleds includes an accelerator sled to receive, with a memory controller, a memory access request from an accelerator device to access a region of memory. The request is to identify the region of memory with a logical address. Additionally, the accelerator sled is to determine from a map of logical addresses and associated physical address, the physical address associated with the region of memory. In addition, the accelerator sled is to route the memory access request to a memory device associated with the determined physical address.