Abstract: Methods and systems for rendering a virtual overlay in an extended reality (XR) environment are described. Image data is received, representing a current field of view (FOV) in the XR environment. A spatial boundary is defined in the current FOV, based on user input. An image label representing a region of interest (ROI) within the defined spatial boundary, and one or more object labels representing one or more objects within the defined spatial boundary are generated. At least one relevant virtual object is identified. The virtual object is relevant to a semantic meaning of the ROI based on the image label and/or the one or more object labels. Identification of the at least one relevant virtual object is outputted, to be renderable in the XR environment.