Abstract: The present application provides a model training method and apparatus, and a prediction method and apparatus, and it relates to fields of artificial intelligence, deep learning, image processing, and autonomous driving. The model training method includes: inputting a first sample image of sample images into a depth information prediction model, and acquiring depth information of the first sample image; acquiring inter-image posture information based on a second sample image of the sample images and the first sample image; acquiring a projection image corresponding to the first sample image, at least according to the inter-image posture information and the depth information; and acquiring a loss function by determining a function for calculating a similarity between the second sample image and the projection image, and training the depth information prediction model using the loss function.

Abstract: A radar point cloud data processing method and device, an apparatus, and storage medium are provided, which are related to technical fields of radar point cloud, automatic driving, and deep learning. An implementation includes: determining a target location area where a target object is located by utilizing a target detection box in the radar point cloud data; removing each point of the target object in the target location area from the radar point cloud data; and adding an object model to the target location area. By applying embodiments of the present disclosure, richer radar point cloud data may be obtained by removing the target object from the radar point cloud data and adding the needed three-dimensional model to the target location area in the radar point cloud data.

Abstract: Provided are a high-precision map construction method, an electronic device, and a storage medium, relating to the field of high-precision map technology and, in particular, to autonomous driving technology. The implementation solution includes: calculating a pose of a camera at each position point according to a pre-acquired video; calculating an absolute depth of each keypoint in the pre-acquired video according to the pose of the camera at each position point; constructing, according to the absolute depth of each keypoint in the video, a corresponding three-dimensional point cloud of each pixel point in the pre-acquired video; and constructing, according to the corresponding three-dimensional point cloud of each pixel point in the pre-acquired video, a high-precision map corresponding to the pre-acquired video.

Abstract: Systems and methods of video inpainting for autonomous driving are disclosed. For example, the method stitches a multiplicity of depth frames into a 3D map, where one or more objects in the depth frames have previously been removed. The method further projects the 3D map onto a first image frame to generate a corresponding depth map, where the first image frame includes a target inpainting region. For each target pixel within the target inpainting region of the first image frame, based on the corresponding depth map, the method further maps the target pixel within the target inpainting region of the first image frame to a candidate pixel in a second image frame. The method further determines a candidate color to fill the target pixel. The method further performs Poisson image editing on the first image frame to achieve color consistency at a boundary and between inside and outside of the target inpainting region of the first image frame.

Abstract: The present application provides a model training method and apparatus, and a prediction method and apparatus, and it relates to fields of artificial intelligence, deep learning, image processing, and autonomous driving. The model training method includes: inputting a first sample image of sample images into a depth information prediction model, and acquiring depth information of the first sample image; acquiring inter-image posture information based on a second sample image of the sample images and the first sample image; acquiring a projection image corresponding to the first sample image, at least according to the inter-image posture information and the depth information; and acquiring a loss function by determining a function for calculating a similarity between the second sample image and the projection image, and training the depth information prediction model using the loss function.

Abstract: Systems and methods of video inpainting for autonomous driving are disclosed. For example, the method stitches a multiplicity of depth frames into a 3D map, where one or more objects in the depth frames have previously been removed. The method further projects the 3D map onto a first image frame to generate a corresponding depth map, where the first image frame includes a target inpainting region. For each target pixel within the target inpainting region of the first image frame, based on the corresponding depth map, the method further maps the target pixel within the target inpainting region of the first image frame to a candidate pixel in a second image frame. The method further determines a candidate color to fill the target pixel. The method further performs Poisson image editing on the first image frame to achieve color consistency at a boundary and between inside and outside of the target inpainting region of the first image frame.

Abstract: A radar point cloud data processing method and device, an apparatus, and storage medium are provided, which are related to technical fields of radar point cloud, automatic driving, and deep learning. An implementation includes: determining a target location area where a target object is located by utilizing a target detection box in the radar point cloud data; removing each point of the target object in the target location area from the radar point cloud data; and adding an object model to the target location area. By applying embodiments of the present disclosure, richer radar point cloud data may be obtained by removing the target object from the radar point cloud data and adding the needed three-dimensional model to the target location area in the radar point cloud data.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for recognizing a face. A specific embodiment of the method includes: acquiring at least two facial images of a to-be-recognized face under different illuminations using a near-infrared photographing device; generating at least one difference image based on a brightness difference between each two of the at least two facial images; determining a facial contour image of the to-be-recognized, face based on the at least one difference image; inputting the at least two facial images, the at least one difference image, and the facial contour image into a pre-trained real face prediction value calculation model to obtain a real face prediction value of the to-be-recognized face; and outputting prompt information for indicating successful recognition of a real face, in response to determining the obtained real face prediction value being greater than a preset threshold.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for recognizing a face. A specific embodiment of the method includes: acquiring at least two facial images of a to-be-recognized face under different illuminations using a near-infrared photographing device; generating at least one difference image based on a brightness difference between each two of the at least two facial images; determining a facial contour image of the to-be-recognized, face based on the at least one difference image; inputting the at least two facial images, the at least one difference image, and the facial contour image into a pre-trained real face prediction value calculation model to obtain a real face prediction value of the to-be-recognized face; and outputting prompt information for indicating successful recognition of a real face, in response to determining the obtained real face prediction value being greater than a preset threshold.