Abstract: A pose estimation method and an apparatus are provided, to obtain a more accurate pose estimation result. The method includes: obtaining a first event image and a first target image, where the first event image is aligned with the first target image in time sequence, the first target image includes an RGB image or a depth image, and the first event image includes an image indicating a movement trajectory that is of a target object and that is generated when the target object moves in a detection range of a motion sensor; determining integration time of the first event image; if the integration time is less than a first threshold, determining that the first target image is not for performing pose estimation; and performing pose estimation based on the first event image.

Abstract: One example image sensor includes a metasurface, a substrate, and an optical-to-electrical converter. Arrays in the metasurface are arranged on the top of the substrate. The metasurface includes multiple subunits. Each subunit includes an array including multiple columnar structures. The bottom of the substrate is disposed on a surface of the optical-to-electrical converter in the image sensor. The metasurface includes at least two media with different refractive indexes. The optical-to-electrical converter includes an array for optical-to-electrical conversion. The array of the optical-to-electrical converter is divided into multiple color regions. The metasurface is configured to refract incident light and transmit, through the substrate, refracted light to a corresponding color region in the array of the optical-to-electrical converter. In addition, each subunit refracts incident light and then transmits refracted light to a color region in a corresponding color unit.