Apple Inc.

Oliver Thomas Ruepp

Jai Prakash

Lina Maria Paz-Perez

Pedro Antonio Pinies Rodriguez

Michele Stoppa

Aitor Aldoma Buchaca

Oliver Montague Welton Dunkley

Vimal Thilak

Chavdar Chavdarov Papazov

Johan Hedborg

Rahul Raguram

Various implementations disclosed herein include devices, systems, and methods for normal estimation using a directional measurement, such as a gravity vector. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes identifying planar surfaces in an environment represented by an image. Each planar surface is associated with a respective orientation. A directional vector associated with the environment is determined. A subset of the planar surfaces that have a threshold orientation relative to the directional vector is identified. For each planar surface in the subset of the planar surfaces, a normal vector for the planar surface is determined based on the orientation of the planar surface and the directional vector.

Normal estimation for a planar surface

Various implementations disclosed herein include devices, systems, and methods for pose estimation using one point correspondence, one line correspondence, and a directional measurement. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes obtaining an image corresponding to a physical environment. A first correspondence between a first set of pixels in the image and a spatial point in the physical environment is determined. A second correspondence between a second set of pixels in the image and a spatial line in the physical environment is determined. Pose information is generated as a function of the first correspondence, the second correspondence, and a directional measurement.

Pose estimation with limited correspondences

In one implementation, a method of estimating the heading of a device is performed by the device including a processor, non-transitory memory, and an image sensor. The method includes determining a geographic location of the device. The method includes capturing, using the image sensor, an image at the geographic location. The method includes detecting one or more lines within the image. The method includes determining a heading of the device based on the one or more lines and the geographic location.

Method and device for heading estimation

In some implementations, a method includes: extracting key-points from a reference image associated with a scene; generating a multi-cone structure including cones based on the key-points and intrinsic parameters, wherein an apex of the cones corresponds to a camera origin point associated with the reference image, and wherein each axis of the cones intersects a respective key-point; aligning the multi-cone structure based on a nominal alignment vector in order to restrict two rotational degrees of freedom; and determining a rigid transformation for the multi-cone structure, including a value for a remaining rotational degree of freedom and values for three translational degrees of freedom, within a search space associated with the scene, wherein a number of the cones within the multi-cone structure that include at least one point in a three-dimensional (3D) point cloud associated with the scene is maximal when the multi-cone structure is transformed by the rigid transformation.

Branch-and-bound search algorithm for 4D camera localization

In accordance with some embodiments, a method is performed at a device with one or more processors, non-transitory memory, and an image sensor. The method includes synthesizing, from image data that corresponds to a physical perspective of an object relative to the device, a surface mask characterizing a portion of a surface of the object based on a grid arranged on the object, wherein the grid is represented in the image data. The method includes generating a virtual perspective of a model associated with the object having a surface oriented to match the surface mask within a predefined confidence threshold.

Method and device for detection and tracking of low-texture objects

In one implementation, a method includes: obtaining an input image, wherein the input image is captured by an image sensor having a rotational orientation with respect to a direction of gravity; obtaining a gravity direction estimation associated with the rotational orientation of the sensor; generating, from the input image, a rotationally preprocessed input image by applying one or more transformations to the input image based on the gravity direction estimation; providing the rotationally preprocessed input image to the machine learning sub-system; and identifying, using the machine learning sub-system, a visual feature within the rotationally preprocessed input image.

Growing community of inventors

Baierbrunn, Germany

Oliver Thomas Ruepp