# US 10,122,996 B2 · Method for 3D multiview reconstruction by feature tracking and model registration

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,122,996 B2
- Document ID: US10122996B2
- Status: Granted
- Kind: B2
- Application number: 15/291,714
- Filed: 2016-10-12
- Published: 2017-09-14
- Granted: 2018-11-06
- Earliest claimed: 2016-03-09
- Assignees: Sony Corporation
- Applicants: Sony Corporation
- Inventors: Ko-Kai Albert Huang; Ming-Chang Liu
- Web page: https://patentgrep.com/patent/US10122996B2

## CPC

- H04N 13/282: for generating image signals corresponding to three or more geometrical viewpoints, e.g. multi-view systems
- G06T 7/579: from motion
- G06T 7/593: from stereo images
- H04N 13/111: Transformation of image signals corresponding to virtual viewpoints, e.g. spatial image interpolation
- H04N 13/128: Adjusting depth or disparity
- H04N 13/239: using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence)
- H04N 13/243: using three or more two-dimensional [2D] image sensors
- G06T 2207/10021: Stereoscopic video; Stereoscopic image sequence
- H04N 2013/0081: {Depth or disparity estimation from stereoscopic image signals}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A 3D multiview reconstruction method takes a sequence of 2D stereo images from a narrow field-of-view imager (e.g., camera) and reconstructs a 3D representation of the wide field-of-view object or scene. The 3D multiview reconstruction method tracks 2D image pixels across neighboring frames and constraints for frame integration via 3D model construction.

## Claims

### Claim 1

A method programmed in a non-transitory memory of a device comprising:
acquiring one or more 2D stereo images;
reconstructing a 3D multiview image using the one or more 2D stereo images, wherein reconstructing the 3D multiview image includes:
rectifying the one or more images;
estimating a disparity between images;
implementing 2D pixel tracking across neighboring frames;
estimating a 3D pose by mapping tracked 2D pixels to 3D coordinates; and
constructing a 3D model based on the 3D pose; and
displaying the 3D multiview image.

### Claim 2 (depends on 1)

The method of claim 1 wherein acquiring the one or more 2D stereo images includes utilizing a plurality of cameras to capture the one or more 2D stereo images.

### Claim 3 (depends on 1)

The method of claim 1 wherein acquiring the one or more 2D stereo images includes downloading the one or more 2D stereo images from a server.

### Claim 4 (depends on 1)

The method of claim 1 wherein the one or more 2D stereo images have a narrow field of view.

### Claim 5 (depends on 1)

The method of claim 1 wherein reconstructing the 3D multiview image includes: selecting a frame of the one or more images;
performing a noise check to discard an image of the one or more images if noise of the image is above a threshold; and
selecting a region of interest in the one or more images.

### Claim 6 (depends on 1)

The method of claim 1 wherein the 3D image comprises a 3D surface.

### Claim 7 (depends on 1)

The method of claim 1 wherein the 3D image comprises a 3D point cloud.

### Claim 8

An apparatus comprising:
a non-transitory memory for storing an application, the application for:
acquiring one or more 2D stereo images;
reconstructing a 3D multiview image using the one or more 2D stereo images, wherein reconstructing the 3D multiview image includes:
rectifying the one or more images;
estimating a disparity between images;
implementing 2D pixel tracking across neighboring frames;
estimating a 3D pose by mapping tracked 2D pixels to 3D coordinates; and
constructing a 3D model based on the 3D pose; and
displaying the 3D multiview image; and
a processing component coupled to the memory, the processing component configured for processing the application.

### Claim 9 (depends on 8)

The apparatus of claim 8 wherein acquiring the one or more 2D stereo images includes utilizing a plurality of cameras to capture the one or more 2D stereo images.

### Claim 10 (depends on 8)

The apparatus of claim 8 wherein acquiring the one or more 2D stereo images includes downloading the one or more 2D stereo images from a server.

### Claim 11 (depends on 8)

The apparatus of claim 8 wherein the one or more 2D stereo images have a narrow field of view.

### Claim 12 (depends on 8)

The apparatus of claim 8 wherein reconstructing the 3D multiview image includes: selecting a frame of the one or more images;
performing a noise check to discard an image of the one or more images if noise of the image is above a threshold; and
selecting a region of interest in the one or more images.

### Claim 13 (depends on 8)

The apparatus of claim 8 wherein the 3D image comprises a 3D surface.

### Claim 14 (depends on 8)

The apparatus of claim 8 wherein the 3D image comprises a 3D point cloud.

### Claim 15

A system comprising:
a plurality of cameras for acquiring one or more 2D stereo images; and
a computing device configured for:
receiving the one or more 2D stereo images;
reconstructing a 3D multiview image using the one or more 2D stereo images, wherein reconstructing the 3D multiview image includes:
rectifying the one or more images;
estimating a disparity between images;
implementing 2D pixel tracking across neighboring frames;
estimating a 3D pose by mapping tracked 2D pixels to 3D coordinates; and
constructing a 3D model based on the 3D pose; and
displaying the 3D multiview image.

### Claim 16 (depends on 15)

The system of claim 15 wherein acquiring the one or more 2D stereo images includes utilizing a plurality of cameras to capture the one or more 2D stereo images.

### Claim 17 (depends on 15)

The system of claim 15 wherein acquiring the one or more 2D stereo images includes downloading the one or more 2D stereo images from a server.

### Claim 18 (depends on 15)

The system of claim 15 wherein the one or more 2D stereo images have a narrow field of view.

### Claim 19 (depends on 15)

The system of claim 15 wherein reconstructing the 3D multiview image includes: selecting a frame of the one or more images;
performing a noise check to discard an image of the one or more images if noise of the image is above a threshold; and
selecting a region of interest in the one or more images.

### Claim 20 (depends on 15)

The system of claim 15 wherein the 3D image comprises a 3D surface.

### Claim 21 (depends on 15)

The system of claim 15 wherein the 3D image comprises a 3D point cloud.
