Various implementations disclosed herein include devices, systems, and methods that generates a three-dimensional (3D) model based on a selected subset of the images and depth data corresponding to each of the images of the subset. For example, an example process may include acquiring sensor data during movement of the device in a physical environment including an object, the sensor data including images of a physical environment captured via a camera on the device, selecting a subset of the images based on assessing the images with respect to motion-based defects based on device motion and depth data, and generating a 3D model of the object based on the selected subset of the images and depth data corresponding to each of the images of the selected subset.

A depth measuring apparatus includes a camera assembly configured to capture a plurality of images of a target at a plurality of distances from the target. The depth measuring apparatus further includes a controller configured to, for each of a plurality of regions within the plurality of images: determine corresponding gradient values within the plurality of images; determine a corresponding maximum gradient value from the corresponding gradient values; and determine, based on the corresponding maximum gradient value, a depth measurement for a region of the plurality of regions.

An image processing device includes a rotation processor and an image processor. The rotation processor receives an input image and generates a temporary image according to the input image. The image processor is coupled to the rotation processor and outputs a processed image according to the temporary image, wherein the image processor has a predetermined image processing width, a width of the input image is larger than the predetermined image processing width, and a width of the temporary image is less than the predetermined image processing width.

Radar, lidar, and other active 3D imaging techniques require large, heavy sensors that consume lots of power. Passive 3D imaging techniques based on feature matching are computationally expensive and limited by the quality of the feature matching. Fortunately, there is a robust, computationally inexpensive way to generate 3D images from full-motion video acquired from a platform that moves relative to the scene. The full-motion video frames are registered to each other and mapped to the scene coordinates using data about the trajectory of the platform with respect to the scene. The time derivative of the registered frames equals the product of the height map of the scene, the projected angular velocity of the platform, and the spatial gradient of the registered frames. This relationship can be solved in (near) real time to produce the height map of the scene from the full-motion video and the trajectory.

The present disclosure relates to methods and devices for performing depth estimation on image data. In one example, a device performs depth estimation on first and second images captured using one or more cameras having a color filter array. Each, image of the first and second images comprises multiple color channels. Each color channel of the multiple color channels corresponds to a respective color channel of the color filter array.sub.. The, device performs the depth estimation by estimating disparity from the color channels of the first and second images.

A 3D image-capturing device that includes at least one camera that acquires a 2D image and distance information of an object, a monitor that displays the 2D image acquired by the camera, and at least one processor including hardware. The processor acquires a first area for which the distance information is not required in the 2D image displayed on the monitor, and sets an image-capturing condition so that the amount of distance information acquired by the camera in the acquired first area is less than or equal to a prescribed first threshold and the amount of distance information acquired by the camera in a second area, which is at least part of an area other than the first area, is greater than a prescribed second threshold that is larger than the first threshold.

A device and method of obtaining a depth of a space are provided. The method includes obtaining a plurality of images by photographing a periphery of a camera a plurality of times while sequentially rotating the camera by a preset angle, identifying a first feature region in a first image and an n-th feature region in an n-th image, the n-th feature region being identical with the first feature region, by comparing adjacent images between the first image and the n-th image from among the plurality of images, obtaining a base line value with respect to the first image and the n-th image, obtaining a disparity value between the first feature region and the n-th feature region, and determining a depth of the first feature region or the n-th feature region based on at least the base line value and the disparity value.

Systems, devices, and methods disclosed herein may generate captured views and a plurality of intermediate views within a pixel disparity range, T.sub.d, the plurality of intermediate views being extrapolated from the captured views.

A multi-viewpoint 3D display screen is provided, comprising: a display panel, having a plurality of composite pixels, wherein each composite pixel in the plurality of composite pixels comprises a plurality of composite subpixels, and each composite subpixel in the plurality of composite subpixels comprises a plurality of subpixels arranged in array; and a plurality of spherical gratings, covering the plurality of composite subpixels. The multi-viewpoint 3D display screen can play a 3D effect for users at different viewing distances, and achieves high-quality 3D quality. A multi-viewpoint 3D display device is also provided.

Systems and methods herein describe using a neural network to identify a first set of joint location coordinates and a second set of joint location coordinates and identifying a three-dimensional hand pose based on both the first and second sets of joint location coordinates.