Matterport, Inc.

An environmental capture system (ECS) captures image data and depth information in a 360-degree scene. The captured image data and depth information can be used to generate a 360-degree scene. The ECS comprises a frame, a drive train mounted to the frame, and an image capture device coupled to the drive train to capture, while pointed in a first direction, a plurality of images at different exposures in a first field of view (FOV) of the 360-degree scene. The ECS further comprises a depth information capture device coupled to the drive train. The depth information capture device and the image capture device are rotated by the drive train about a first, substantially vertical, axis from the first direction to a second direction. The depth information capture device, while being rotated from the first direction to the second direction, captures depth information for a first portion of the 360-degree scene. The image capture device captures, while pointed in the second direction, a plurality of images at different exposures in a second FOV that overlaps the first FOV of the 360-degree scene. The depth information capture device and the image capture device are rotated by the drive train about the first axis from the second direction to a third direction. The depth information capture device, while being rotated from the second direction to the third direction, captures depth information for a second portion of the 360-degree scene. The image capture device, while pointed in the third direction, captures a plurality of images at different exposures in a third FOV that overlaps the second FOV of the 360-degree scene.

Systems and methods for building a three-dimensional composite scene are disclosed. Certain embodiments of the systems and methods may include the use of a three-dimensional capture device that captures a plurality of three-dimensional images of an environment. Some embodiments may further include elements concerning aligning and/or mapping the captured images. Various embodiments may further include elements concerning reconstructing the environment from which the images were captured. The methods disclosed herein may be performed by a program embodied on a non-transitory computer-readable storage medium when executed the program is executed a processor.

An apparatus comprising a housing, a mount configured to be coupled to a motor to horizontally move the apparatus, a wide-angle lens coupled to the housing, the wide-angle lens being positioned above the mount thereby being along an axis of rotation, the axis of rotation being the axis along which the apparatus rotates, an image capture device within the housing, the image capture device configured to receive two-dimensional images through the wide-angle lens of environment, and a LiDAR device within the housing, the LiDAR device configured to generate depth data based on the environment.

An apparatus comprising a housing, a mount configured to be coupled to a motor to horizontally move the apparatus, a wide-angle lens coupled to the housing, the wide-angle lens being positioned above the mount thereby being along an axis of rotation, the axis of rotation being the axis along which the apparatus rotates, an image capture device within the housing, the image capture device configured to receive two-dimensional images through the wide-angle lens of environment, and a LiDAR device within the housing, the LiDAR device configured to generate depth data based on the environment.

Techniques are provided for increasing the accuracy of automated classifications produced by a machine learning engine. Specifically, the classification produced by a machine learning engine for one photo-realistic image is adjusted based on the classifications produced by the machine learning engine for other photo-realistic images that correspond to the same portion of a 3D model that has been generated based on the photo-realistic images. Techniques are also provided for using the classifications of the photo-realistic images that were used to create a 3D model to automatically classify portions of the 3D model. The classifications assigned to the various portions of the 3D model in this manner may also be used as a factor for automatically segmenting the 3D model.

The disclosed subject matter is directed to employing machine learning models configured to predict 3D data from 2D images using deep learning techniques to derive 3D data for the 2D images. In some embodiments, a method is provided that comprises receiving, by a system comprising a processor, a panoramic image, and employing, by the system, a three-dimensional data from two-dimensional data (3D-from-2D) convolutional neural network model to derive three-dimensional data from the panoramic image, wherein the 3D-from-2D convolutional neural network model employs convolutional layers that wrap around the panoramic image as projected on a two-dimensional plane to facilitate deriving the three-dimensional data.

Techniques are provided for increasing the accuracy of automated classifications produced by a machine learning engine. Specifically, the classification produced by a machine learning engine for one photo-realistic image is adjusted based on the classifications produced by the machine learning engine for other photo-realistic images that correspond to the same portion of a 3D model that has been generated based on the photo-realistic images. Techniques are also provided for using the classifications of the photo-realistic images that were used to create a 3D model to automatically classify portions of the 3D model. The classifications assigned to the various portions of the 3D model in this manner may also be used as a factor for automatically segmenting the 3D model.

The disclosed subject matter is directed to employing machine learning models configured to predict 3D data from 2D images using deep learning techniques to derive 3D data for the 2D images. In some embodiments, a method is provided that comprises receiving, by a system comprising a processor, a panoramic image, and employing, by the system, a three-dimensional data from two-dimensional data (3D-from-2D) convolutional neural network model to derive three-dimensional data from the panoramic image, wherein the 3D-from-2D convolutional neural network model employs convolutional layers that wrap around the panoramic image as projected on a two-dimensional plane to facilitate deriving the three-dimensional data.

An environmental capture system (ECS) captures image data and depth information in a 360-degree scene. The captured image data and depth information can be used to generate a 360-degree scene. The ECS comprises a frame, a drive train mounted to the frame, and an image capture device coupled to the drive train to capture, while pointed in a first direction, a plurality of images at different exposures in a first field of view (FOV) of the 360-degree scene. The ECS further comprises a depth information capture device coupled to the drive train. The depth information capture device and the image capture device are rotated by the drive train about a first, substantially vertical, axis from the first direction to a second direction. The depth information capture device, while being rotated from the first direction to the second direction, captures depth information for a first portion of the 360-degree scene. The image capture device captures, while pointed in the second direction, a plurality of images at different exposures in a second FOV that overlaps the first FOV of the 360-degree scene. The depth information capture device and the image capture device are rotated by the drive train about the first axis from the second direction to a third direction. The depth information capture device, while being rotated from the second direction to the third direction, captures depth information for a second portion of the 360-degree scene. The image capture device, while pointed in the third direction, captures a plurality of images at different exposures in a third FOV that overlaps the second FOV of the 360-degree scene.

Systems and methods for building a three-dimensional composite scene are disclosed. Certain embodiments of the systems and methods may include the use of a three-dimensional capture device that captures a plurality of three-dimensional images of an environment. Some embodiments may further include elements concerning aligning and/or mapping the captured images. Various embodiments may further include elements concerning reconstructing the environment from which the images were captured. The methods disclosed herein may be performed by a program embodied on a non-transitory computer-readable storage medium when executed the program is executed a processor.