Snap Inc.

Denys Makoviichuk

Yurii Monastyrshyn

Gabriel Lupin

Travis Chen

Oleksii Kholovchuk

Artem Yerofieiev

Artem Gaiduchenko

Bohdan Pozharskyi

Sergey Tulyakov

Jian Ren

Vladislav Shakhrai

Ju Hu

Pavlo Chemerys

Junli Cao

A neural light field (NeLF) that runs real-time on mobile devices for neural rendering of three dimensional (3D) scenes, referred to as MobileR2L. The MobileR2L architecture runs efficiently on mobile devices with low latency and small size, and it achieves high-resolution generation while maintaining real-time inference for both synthetic and real-world 3D scenes on mobile devices. The MobileR2L has a network backbone including a convolutional layer embedding an input image at a resolution, residual blocks uploading the embedded image, and super-resolution modules receiving the uploaded embedded image and rendering an output image having a higher resolution than the embedded image. The convolution layer generates a number of rays equal to a number of pixels in the input image, where a partial number of the rays is uploaded to the super-resolution modules.

Real-time neural light field on mobile devices

Method for generating a live streaming video having real-time special effects starts with a processor displaying on a display device a lens selection user interface including a plurality of lens selections. The lens selections are associated with a plurality of special effects, respectively, and include a first lens selection associated with a first special effect and a second lens selection associated with a second special effect. The processor then receiving a selection of the first lens selection and applies in real-time the first special effect to a video stream captured by a camera to generate a video stream having the first special effect. The processor then transmits in real-time the video stream having the first special effect via a network to be displayed on a plurality of client devices. Other embodiments are disclosed.

Generating a live streaming video having real-time special effects

Method for triggering changes to real-time special effects included in a live streaming video starts with a processor transmitting in real-time a video stream captured by a camera via a network. The processor causes a live streaming interface that includes the video stream to be displayed on the plurality of client devices. The processor receives a trigger to apply one of a plurality of special effects to the video stream and determines a first special effect of the plurality of special effects is associated with the trigger. The processor applies in real-time the first special effect to the video stream to generate a video stream having the first special effect and transmits in real-time the video stream having the first special effect via the network. The processor causes the live streaming interface that includes the video stream having the first special effect to be displayed on the plurality of client devices. Other embodiments are disclosed.

Triggering changes to real-time special effects included in a live streaming video

Growing community of inventors

Marina Del Rey, CA, United States of America

Denys Makoviichuk