Back to results
US 2026/0148490 A1Published application
Interactive image generation
AssigneeOutward, Inc.
InventorsClarence Chui, Manu Parmar, Akshansh Chaudhry, Himanshu Jain, Andrew Pang, Lakshay Sharma, Brook Aaron Seaton
Life of this patent
Estimating the term…
Abstract
A content generation platform is generally described herein. More specifically, interactive image generation and techniques and features thereof are disclosed herein. An arbitrary input image captured in an unknown environment is processed using one or more machine learning based networks to generate an interactive reconstruction or floorplan of the input image.
Claims20
A method, comprising:
- receiving an input image of a scene having undefined characteristics;
- processing the received input image of the scene having undefined characteristics using one or more machine learning based networks;
- and
- generating an interactive reconstruction of the scene based on processing the received input image of the scene having undefined characteristics using the one or more machine learning based networks, wherein interactive features of the generated interactive reconstruction of the scene are facilitated by the one or more machine learning based networks having at least in part learned the interactive features from training images generated from corresponding three-dimensional models.
1 more element
A system, comprising:
- a processor configured to:
- receive an input image of a scene having undefined characteristics;
- process the received input image of the scene having undefined characteristics using one or more machine learning based networks;
- and
- generate an interactive reconstruction of the scene based on processing the received input image of the scene having undefined characteristics using the one or more machine learning based networks, wherein interactive features of the generated interactive reconstruction of the scene are facilitated by the one or more machine learning based networks having at least in part learned the interactive features from training images generated from corresponding three-dimensional models;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
4 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- receiving an input image of a scene having undefined characteristics;
- processing the received input image of the scene having undefined characteristics using one or more machine learning based networks;
- and
- generating an interactive reconstruction of the scene based on processing the received input image of the scene having undefined characteristics using the one or more machine learning based networks, wherein interactive features of the generated interactive reconstruction of the scene are facilitated by the one or more machine learning based networks having at least in part learned the interactive features from training images generated from corresponding three-dimensional models.
1 more element
Dependencies are inferred from the claim text.