2D-to-3D conversion method for video
A conversion method and video technology, applied in machine learning, instrumentation, computing, etc., can solve the problems of large black hole areas that cannot be filled, inaccurate depth estimation, and slow three-dimensional conversion speed, etc., to achieve excellent rendering effects, improve detailed textures, reduce The effect of object deformation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0064] Such as figure 1 As shown, this embodiment provides a specific 2D-to-3D video conversion method, using a deep learning model to replace the depth map estimation algorithm and black hole filling algorithm in the traditional DIBR method, using the high generalization and high precision of the deep learning model, etc. characteristics, making up for the deficiencies in traditional algorithms. Based on the Tensorflow framework, an efficient and high-quality conversion technology is realized.
[0065] The invention is a 2D / 3D conversion method aimed at 2K resolution and above. Based on the Tensorflow open source framework, the CUDA engine is used to accelerate parallel computing, and the 2D / 3D conversion on the ultra-high resolution image is realized. The original image and mask are sent to the depth estimation model to generate the left and right projection images, such as figure 2 As shown, the depth image containing the black hole is repaired into a complete image as ...
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