Other

Disney Enterprises, Inc.

On2.com, Inc.

Blake G Sloan

Richard Steven Adler

Michael O Maloney

Edwin L Jesse

David Harrison Silver

Tunc Ozan Aydin

Eric Ameres

Yang Zhang

Daniel M Miller

George E Nelson

Keith T O'Brien

Vince Cerundolo

Steven S Shapiro

Timothy S Murphy

Jeroen Schulte

The exemplary embodiments relate to converting Standard Dynamic Range (SDR) content to High Dynamic Range (HDR) content using a machine learning system. In some embodiments, the neural network is trained to convert an input SDR image into an HDR image using the encoded representation of a training SDR image and a training HDR image. In other embodiments, the neural network is trained to convert an input SDR image into an HDR image using a predefined set of color grading actions and the training images.

Deep SDR-HDR conversion

A process receives, with a processor, a plurality of image device properties corresponding to an image capture device. Further the process selects, with the processor, one or more of the plurality of image device properties based on one or more pipeline criteria. The pipeline criteria indicate one or more weights corresponding to the plurality of image device properties. Additionally, the process truncates, with the processor, the one or more selected image device properties to a predetermined number of characters based on a human readability factor. The human readability factor is provided by the one or more pipeline criteria. The process automatically generates, with the processor, a device parameter data structure by ordering the truncated one or more image device properties according to the one or more weights. Moreover, the process transmits, with the processor, the device parameter data structure through a video post-production pipeline.

Code generation system for image capture device parameters

This invention uses a novel synthesis of several different compression methods, some original and some known in the art, to achieve compression of digitized video image sequences. Images are color-reduced by a factor of two in both directions using a colorspace that requires minimal computation for reconstruction of RGB pixel values. Images are then transformed into a `token sequence` corresponding to a series of 4.times.4 blocks, using one of seven transformation methods, some dependent on previous frames and some dependent only on pixel values in neighboring blocks. The resulting token sequence is then compressed using known lossless methods, including Huffman coding.

Method and apparatus for compression and decompression of video images

An automatically-actuated sealing device is disclosed which seals a gap between a door bottom (or edge) and a surface defining part of an opening through which weather, dust, insects, etc. may otherwise pass. The sealing device includes a support element attachable to the door bottom, a seal actuating element movably supported by the support element, a sealing element moved by the seal actuating element into a sealing position, and a plurality of metal, plastic or metal and plastic spring elements which couple the seal actuating element to the support element and urge the seal actuating element to seal the gap. The sealing devices operate by coupling the device to the opening defining surface so that opening and closing of the door generates movement of the seal actuating element. A projection on the seal actuating element is engaged by the door jamb or a bearing element attached to the jamb, and is laterally moved in response to opening and closing the door. In another embodiment, spring elements direct movement of the seal actuating member without lateral movement using a cord attached to the seal actuating element and the opening defining surface. The sealing device may be mounted to either side of or in an edge (mortise-mounted) of the door, and to both right and left-opening doors. A one-piece cover with end caps covers the sealing device. The support element is attached to the door using a few screws; everything else, including the cover and end caps, is attached without fasteners.

Automatic door sweep

A sealing device automatically seals a gap between a door bottom and a floor in response to closing movement of the door. The sealing device includes a support element attachable to the door bottom, a seal actuating element movably supported from the support element by spring elements, and a sealing element carried by the seal actuating element. The sealing device may be mounted to the inside or outside of a door, or mortise-mounted in the door, and may be mounted to left- or right-opening hinged doors, or to sliding or articulated closures, and may be provided as an after market or OEM device. The spring elements in the preferred embodiment are one-piece and are integrally connected to both the support element and the seal actuating element, thereby forming a one-piece sealing device preferably made of plastic. In embodiments where lateral movement of the seal actuating element is required to seal the gap, a projection on the seal actuating element is engaged by a door jamb surface or an element attached thereto during door opening and closing. A cover for the device is attached without fasteners e.g., by snap-fitting or slide fitting, and may act as a kick plate, and may be decorative. The length of the sealing device may be easily reduced or expanded to fit various size doors. The invention also provides a device which holds the seal actuating element a predetermined distance from the support element during installation of the device on the door to facilitate installation.

Growing community of inventors

New York, NY, United States of America

Blake G Sloan