Generating high-quality, realistic rendering images for real-time applications generally requires tracing a few samples-per-pixel (spp) and using deep learning-based approaches to denoise the resulting low-spp images. Existing denoising methods necessitate a substantial time expenditure when rendering at high resolutions due to the physically-based sampling and network inference time burdens. In this paper, we propose a novel Monte Carlo sampling strategy to accelerate the sampling process and a corresponding denoiser, subpixel sampling reconstruction (SSR), to obtain high-quality images. Extensive experiments demonstrate that our method significantly outperforms previous approaches in denoising quality and reduces overall time costs, enabling real-time rendering capabilities at 2K resolution.

The ability of a vehicle following system to establish and maintain a safe and efficient steady-following (SESF) state, recover a previous SESF state, and create a new SESF state is crucial for assessing and demonstrating the levels of automation and intelligence in vehicle following systems and unmanned autonomous vehicles. To endow the vehicle-following system with this ability, the SESF state is defined as the target for controlling and optimizing vehicle-following behavior. Building on this definition, we explore the control mechanisms governing the establishment and maintenance of a SESF state, the recovery of a previous SESF state, and the recreation of a new SESF state within the vehicle-following system. Guided by these mechanisms, we construct an SESF state-oriented model predictive control (MPC) model, leveraging real-time tracking of dynamic safety inter-vehicle distance. Subsequently, a hierarchical algorithm is designed, incorporating a SESF state-oriented global process optimization alongside safety and comfort constraints. This approach aims to enhance the performance of vehicle-following control towards SESF state. Simulation results confirm that when the preceding vehicle maintains a constant velocity for a sufficient duration, the following vehicle, employing the proposed control method, adjusts its behavior to achieve the SESF state while ensuring safety, efficiency, and smoothness. The validation results underscore the viability and effectiveness of the SESF state-oriented vehicle following control method in establishing, maintaining, recovering, and creating the SESF state. These findings provide nuanced perspectives for optimizing and controlling vehicle following behavior.