Abstract: The present disclosure provides a method for regulating a quality of an oil derived from plastic wastes by supercritical hydrothermal liquefaction, including catalyst synthesis, calcination, and supercritical hydrothermal liquefaction. In the present disclosure, a catalyst is prepared by the method, and then applied in regulating the quality of the oil derived from plastic wastes by supercritical hydrothermal liquefaction. This not only reduces cost, but also optimizes a reaction process, such that plastics can be recycled as resources, thereby reducing the carbon emissions and promoting the development of circular economy. The method has strong practicability and functionality, and can be widely used in the technical fields of harmless treatment and resource utilization of plastic waste.

Abstract: A method, apparatus, and system for generating tight two-dimensional (2D) bounding boxes for visible objects in a three-dimensional (3D) scene is disclosed. A two-dimensional (2D) segmentation image of a three-dimensional (3D) scene comprising one or more objects is generated by rendering the 3D scene with a segmentation camera. Each of the objects is rendered in a single respective different color. Next, one or more visible objects in the 3D scene are identified among the one or more objects based on the segmentation image. Next, a 2D amodal segmentation image for each of the visible objects in the 3D scene is generated separately. Each amodal segmentation image comprises only the single visible object for which it is generated. Thereafter, a 2D bounding box is generated for each of the visible objects in the 3D scene based on the amodal segmentation image for the visible object.

Abstract: A method, apparatus, and system for generating a target distorted image from a synthetic distortion-less source cubemap image is disclosed. A synthetic distortion-less source cubemap image is generated. For each pixel on a target distorted image, a pixel on the source cubemap image that corresponds to the pixel on the target distorted image is determined. For each pixel on the target distorted image, a color of the corresponding pixel on the source cubemap image is determined. Thereafter, a same color as the determined color of the corresponding pixel on the source cubemap image is filled in at each pixel on the target distorted image.

Abstract: A method, apparatus, and system for generating a target distorted image from a synthetic distortion-less source cubemap image is disclosed. A synthetic distortion-less source cubemap image is generated. For each pixel on a target distorted image, a pixel on the source cubemap image that corresponds to the pixel on the target distorted image is determined. For each pixel on the target distorted image, a color of the corresponding pixel on the source cubemap image is determined. Thereafter, a same color as the determined color of the corresponding pixel on the source cubemap image is filled in at each pixel on the target distorted image.

Abstract: A method, apparatus, and system for generating tight two-dimensional (2D) bounding boxes for visible objects in a three-dimensional (3D) scene is disclosed. A two-dimensional (2D) segmentation image of a three-dimensional (3D) scene comprising one or more objects is generated by rendering the 3D scene with a segmentation camera. Each of the objects is rendered in a single respective different color. Next, one or more visible objects in the 3D scene are identified among the one or more objects based on the segmentation image. Next, a 2D amodal segmentation image for each of the visible objects in the 3D scene is generated separately. Each amodal segmentation image comprises only the single visible object for which it is generated. Thereafter, a 2D bounding box is generated for each of the visible objects in the 3D scene based on the amodal segmentation image for the visible object.