Method for complementing object shape in RGBD image
A technology in the shape and image of objects, applied in the field of 3D geometric modeling, it can solve problems such as loss of geometric details, and achieve the effect of simplifying complex processes
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0066] The inventor has implemented the embodiment of the present invention on a desktop computer equipped with an Intel I5-4430 central processing unit, Nvidia GeForce GTX760 graphics card and 16GB memory.
[0067] The inventor used Microsoft Kinect to collect RGBD images of objects in multiple categories (such as chairs, tables, statues, bicycles, containers, toys, etc.), and used the public data set released by the US UIUC to test the experimental results of the invention. The results show that, in our current hardware configuration, the present invention can complement a large amount of geometric information missing from objects in a single RGBD image in a relatively short time. Although the initial solution obtained by the data-driven method is very different from the input data in terms of geometry and topology, the optimization algorithm based on volume matching of the present invention can be very good by combining surface confidence constraints, visibility constraints and...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com