Abstract: System and method embodiments are disclosed for wireless channel information sharing to improve system performance in a wireless communication system. A software convergence layer is incorporated to query and keep track of all clients connected with the wireless communication system through different wireless technologies, such as 5G and/or WLAN. The shared channel information may be modeled into a set of coordinates. For each coordinate, a set of operational parameters, such as beamforming weights, Tx and Rx rate, Tx power, and Rx gain on a per-channel basis are determined. These operational parameters are passed onto schedulers of the different wireless technologies, which then use these operational parameters when clients are around corresponding coordinates.

Abstract: Improved techniques for performing object segmentation are disclosed. Surface reconstruction (SR) data corresponding to an environment is accessed. This SR data is used to generate a detailed three-dimensional (3D) representation of the environment. The SR data is also used to infer a high-level 3D structural representation of the environment. The high-level 3D structural representation is inferred using machine learning that is performed on the surface reconstruction data to identify a structure of the environment. The high-level 3D structural representation is then cut from the detailed 3D representation. This cutting process generates a clutter mesh comprising objects that remain after the cut and that are distinct from the structure. Object segmentation is then performed on the remaining objects to identify those objects.

Abstract: Improved techniques for performing object segmentation are disclosed. Surface reconstruction (SR) data corresponding to an environment is accessed. This SR data is used to generate a detailed three-dimensional (3D) representation of the environment. The SR data is also used to infer a high-level 3D structural representation of the environment. The high-level 3D structural representation is inferred using machine learning that is performed on the surface reconstruction data to identify a structure of the environment. The high-level 3D structural representation is then cut from the detailed 3D representation. This cutting process generates a clutter mesh comprising objects that remain after the cut and that are distinct from the structure. Object segmentation is then performed on the remaining objects to identify those objects.