Patent
Method and apparatus for image conversion
TLDR
In this article, a method and apparatus for image conversion according to an embodiment of the present disclosure includes receiving original image data, separating the original data into a front view image and a back view image, and generating a converted 3D image by restoring a background space between the front view images and the back view images using a 3D conversion processing neural network.Abstract:
A method and apparatus for image conversion according to an embodiment of the present disclosure includes receiving original image data, separating the original image data into a front view image and a back view image for performing 3D conversion processing of the original image data, and generating a converted 3D image by restoring a background space between the front view image and the back view image using a 3D conversion processing neural network. The 3D conversion processing neural network according to the present disclosure may be a deep neural network generated by machine learning, and input and output of images may be performed in an Internet of things environment using a 5G network.read more
References
More filters
Patent
2D to 3D video conversion
Haohong Wang,Glenn Adler +1 more
TL;DR: In this article, a method for real-time 2D to 3D video conversion is proposed, where a decoded 2D video frame has an original resolution, and a frame depth map in the original resolution is derived based on the background depth map and the foreground depth map.
Patent
Mixed reality simulation system for testing vehicle control system designs
TL;DR: In this paper, the authors present a system, method, and tangible memory for generating a simulation of a vehicle environment that synthesises the real-world active agents with 3D models of active agents and synthesizes the realworld environmental elements with the 3D model of environmental elements.
Patent
Automatic background replacement for single-image and multi-view captures
Holzer Stefan Johannes Josef,Reso Matthias,Kar Abhishek,Santiago Julius,Hanchar Pavel,Rusu Radu Bogdan +5 more
TL;DR: In this article, a segmentation of an object depicted in a first visual representation is determined, where the segmentation may include for each image a first respective image portion that includes the object, a second respective image part that includes a respective ground area located beneath the object and a third respective image region that includes background area located above the second respective portion and behind the object.
Patent
Dynamic chroma key for video background replacement
TL;DR: In this article, a method, a device, and a computer program product for background image replacement in image data is presented, which includes receiving, from at least one image sensor of a mobile device, frame data.
Patent
Joint training technique for depth map generation
TL;DR: In this article, a joint training technique for depth map generation implemented by depth prediction system as part of a computing device is described, which is configured to generate a candidate feature map from features extracted from training digital images.