18055585. MODIFYING TWO-DIMENSIONAL IMAGES UTILIZING SEGMENTED THREE-DIMENSIONAL OBJECT MESHES OF THE TWO-DIMENSIONAL IMAGES simplified abstract (ADOBE INC.)
Contents
- 1 MODIFYING TWO-DIMENSIONAL IMAGES UTILIZING SEGMENTED THREE-DIMENSIONAL OBJECT MESHES OF THE TWO-DIMENSIONAL IMAGES
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 MODIFYING TWO-DIMENSIONAL IMAGES UTILIZING SEGMENTED THREE-DIMENSIONAL OBJECT MESHES OF THE TWO-DIMENSIONAL IMAGES - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 How does this technology compare to existing methods of generating three-dimensional meshes from two-dimensional images?
- 1.11 What are the limitations of using neural networks for determining density values and camera parameters in this context?
- 1.12 Original Abstract Submitted
MODIFYING TWO-DIMENSIONAL IMAGES UTILIZING SEGMENTED THREE-DIMENSIONAL OBJECT MESHES OF THE TWO-DIMENSIONAL IMAGES
Organization Name
Inventor(s)
Radomir Mech of Mountain View CA (US)
Nathan Carr of San Jose CA (US)
Matheus Gadelha of San Jose CA (US)
MODIFYING TWO-DIMENSIONAL IMAGES UTILIZING SEGMENTED THREE-DIMENSIONAL OBJECT MESHES OF THE TWO-DIMENSIONAL IMAGES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18055585 titled 'MODIFYING TWO-DIMENSIONAL IMAGES UTILIZING SEGMENTED THREE-DIMENSIONAL OBJECT MESHES OF THE TWO-DIMENSIONAL IMAGES
Simplified Explanation
The patent application describes a system for generating three-dimensional meshes representing two-dimensional images for editing purposes. The system utilizes neural networks to determine density values of pixels, sample points in the image, generate a tessellation, estimate camera parameters, and modify the mesh based on the camera parameters.
- Neural networks are used to determine density values of pixels in a two-dimensional image.
- Points are sampled in the image based on the density values to generate a tessellation.
- A second neural network estimates camera parameters and modifies the three-dimensional mesh accordingly.
- The system can also modify the two-dimensional image based on a displacement input.
Potential Applications
This technology could be used in:
- Graphic design software
- Virtual reality applications
- Augmented reality applications
Problems Solved
This technology solves problems related to:
- Editing two-dimensional images in a more intuitive way
- Creating realistic three-dimensional representations of two-dimensional images
Benefits
The benefits of this technology include:
- Improved editing capabilities for images
- Enhanced visualization of two-dimensional images in three dimensions
- Increased efficiency in editing workflows
Potential Commercial Applications
Potential commercial applications of this technology include:
- Software development for graphic designers
- Integration into virtual and augmented reality platforms
- Tools for architects and interior designers
Possible Prior Art
One possible prior art for this technology could be:
- Existing 3D modeling software that allows for the conversion of 2D images into 3D models.
Unanswered Questions
How does this technology compare to existing methods of generating three-dimensional meshes from two-dimensional images?
This article does not provide a direct comparison to existing methods, so it is unclear how this technology differs or improves upon current techniques.
What are the limitations of using neural networks for determining density values and camera parameters in this context?
The article does not address any potential limitations or challenges that may arise from using neural networks for these specific tasks.
Original Abstract Submitted
Methods, systems, and non-transitory computer readable storage media are disclosed for generating three-dimensional meshes representing two-dimensional images for editing the two-dimensional images. The disclosed system utilizes a first neural network to determine density values of pixels of a two-dimensional image based on estimated disparity. The disclosed system samples points in the two-dimensional image according to the density values and generates a tessellation based on the sampled points. The disclosed system utilizes a second neural network to estimate camera parameters and modify the three-dimensional mesh based on the estimated camera parameters of the pixels of the two-dimensional image. In one or more additional embodiments, the disclosed system generates a three-dimensional mesh to modify a two-dimensional image according to a displacement input. Specifically, the disclosed system maps the three-dimensional mesh to the two-dimensional image, modifies the three-dimensional mesh in response to a displacement input, and updates the two-dimensional image.
