Disney Enterprises, Inc.

Other

David M Adler

Fabrice Pierre Armand Rousselle

Oliver Wang

Alexander Sorkine Hornung

Brent Burley

Henning Zimmer

Wojciech Krzysztof Jarosz

Olga Sorkine Hornung

Wenzel Jakob

Christopher Richard Schroers

Jan Novak

Thijs Vogels

Marios Papas

Gregory Nichols

Ralf Habel

Giovanni Colombo

Farnood Salehi

Colin Smith

Marco Manzi

Henrik D Dahlberg

Gerhard Röthlin

Andre C Mazzone

Per H Christensen

Mark A Meyer

Jonathan Hartzberg

Delio Aleardo Vicini

Certain aspects of the present disclosure provide techniques for adaptive sampling for rendering using deep learning. This includes receiving, at a sampler in a rendering pipeline, a plurality of rendered pixel data, wherein the sampler includes a first machine learning (ML) model. It further includes generating a sampling map for the rendering pipeline using the first ML model and the plurality of rendered pixel data, including predicting a plurality of pixel values in the sampling map based on a generated distribution of pixel values. It further includes rendering an image using the sampler, the sampling map, and a denoiser in the rendering pipeline.

Adaptive sampling using deep learning

According to one implementation, a media content conformation system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive an editing file including edits to media content, the edits being based on a compressed representation of the media content and having a first data format. The software code also obtains cross-referencing data that maps a timecode data of the compressed representation of the media content to segments of an uncompressed representation of the media content, and transforms the editing file to a conformation file including the edits in a second data format based on the cross-referencing data. The conformation file enables rendering of an edited version of the media content including the edits.

Digital conformation of media content

Particular embodiments perform a light path analysis of an image comprising a scene, wherein the scene comprises at least one refractive or reflective object. The image may be decomposed based on the light path analysis into a plurality of components, each of the components representing a contribution to lighting in the scene by a different type of light interaction. For each of the components, one or more motion vectors are extracted for each of the components in order to capture motion in the scene. Finally, a final contribution of each of the components to the image is computed based on the motion vectors.

Image decomposition and path-space motion estimation

Particular embodiments decompose an image comprising a scene into a diffuse component and a specular component. Each of the components represent a contribution to lighting in the scene. A set of motion vectors may be extracted in order to capture motion in the scene. Finally, a final contribution of each of the components to the image may be computed based on the motion vectors.

According to one implementation, an image rendering system includes a computing platform having a hardware processor and a system memory storing an image denoising software code. The hardware processor executes the image denoising software code to receive an image file including multiple pixels, each pixel containing multiple depth bins, and to select a pixel including a noisy depth bin from among the pixels for denoising. The hardware processor further executes the image denoising software code to identify a plurality of reference depth bins from among the depth bins contained in one or more of the pixels, for use in denoising the noisy depth bin, and to denoise the noisy depth bin using an average of depth bin values corresponding respectively to each of the reference depth bins.

Denoising binned-depth images

There is provided a scene rendering system and method for use by such a system to perform depth buffering for subsequent scene rendering. The system includes a memory storing a depth determination software including a reduced depth set identification software module, and a hardware processor configured to execute the depth determination software. The hardware processor is configured to execute the depth determination software to determine, before rendering a scene, a depth buffer based on at least one fixed depth identified for each element of a rendering framework for the scene. The hardware processor is further configured to render the scene using the depth buffer.

Depth buffering for subsequent scene rendering

An exercise device having a weighted and padded cross arm on a post extending up from the base of the device. The base has a channel-shaped front end for snugly engaging the foot of a bed mattress. The base has a flat bottom segment extending rearward from its channel-shaped front end and a flat back segment hinged to the back end of the bottom segment.

Exercise device

Growing community of inventors

Valley Glen, CA, United States of America

David M Adler