The proliferation of immersive 3D web applications, from e-commerce product viewers to virtual real estate tours, has created a critical need for high-quality, real-time rendering directly within the browser. Neural radiance fields (NeRF) offer unprecedented photorealism but are hamstrung by immense computational demands, making their deployment on resource-constrained web platforms a significant web engineering challenge. The core bottleneck is NeRF’s reliance on dense point sampling for volume rendering. This paper introduces a novel framework that directly tackles this challenge through a pioneering adaptive sampling technique powered by reinforcement learning. We name this framework PPO-NeRF. It integrates the rapid training capabilities of Instant-NGP’s hash encoding with an agent trained via proximal policy optimization (PPO). This agent learns to adaptively predict the minimal set of crucial sample points along each camera ray, dynamically pruning computationally redundant samples to optimize rendering specifically for web-based, real-time scenarios. Experimental results demonstrate that PPO-NeRF significantly lowers the barrier to web deployment. Compared to the original NeRF, it reduces training time by approximately 73.63%, enabling faster content iteration for web developers. More critically, our adaptive sampling slashes rendering time by approximately 44.7% and VRAM usage by approximately 29.9%, while maintaining comparable visual fidelity. These gains directly translate to faster load times, smoother user interaction, and broader device compatibility. In conclusion, PPO-NeRF provides a practical solution to NeRF’s long-standing performance bottlenecks, establishing a viable pathway for deploying high-fidelity, interactive 3D experiences at scale across the modern web.

As modern smart-factory environments increasingly require real-time remote operation and lightweight cloud-based control, routing intelligence for OHT systems must be fully web-app compatible, supporting scalable deployment without reliance on high-end local infrastructure. To address these demands and the limitations of static algorithms in large-scale OHT systems, this study proposes a multi-agent reinforcement learning model based on proximal policy optimization, incorporating a state space that accounts for chain blockage probability. The key metric, “movement success probability,” integrates preceding agent states to predictively assess chain-reaction congestion, enabling agents to proactively select stable detours. To enhance scalability in high-density environments, the model stabilizes learning through a lightweight policy initialization approach rather than requiring large-scale training from scratch. Moreover, the proposed decentralized structure minimizes central computational overhead, aligning naturally with web-app deployment and enabling real-time monitoring across distributed environments. In a simulation with 1333 nodes and 100 OHTs, the proposed model achieved an average task completion distance of 166,809 mm, improving efficiency by 4.1% over the rule-based Floyd–Warshall method (173,940 mm). Notably, in worst-case scenarios where the rule-based method surged to 321,753 mm due to congestion, the AI model maintained 176,268 mm, achieving a 45.2% reduction and demonstrating superior operational stability.

In recent years, 3D reconstruction and rendering technologies have become increasingly important in various web-based applications within the field of web technology. In particular, with the emergence of technologies such as WebGL and WebGPU, which enable real-time 3D content rendering in web browsers, immersive experiences and interactions on the web have been significantly enhanced. These technologies are widely used in applications such as 3D visualization of virtual products or 3D exploration of building interiors on real estate websites. Through these advancements, users can experience 3D content directly in their browsers without the need to install additional software, greatly expanding the possibilities of the web. Amidst this trend, the neural radiance field (NeRF) has garnered attention as a cutting-edge technology that improves the accuracy of 3D reconstruction and rendering. NeRF is a technique widely used in computer vision and graphics for reconstructing 3D spaces from 2D images taken from multiple viewpoints. By predicting the color and density of each pixel, NeRF captures the complex 3D structure and optical properties of a scene, enabling highly accurate 3D reconstructions. However, NeRF’s primary limitation is the time-consuming nature of both the training and inference processes. Research efforts to address this issue have focused on two key areas: optimizing network architectures and training procedures to accelerate scene learning, and improving inference speed for faster rendering. While progress has been made in enhancing training speed, challenges remain in improving the inference process. To address these limitations, we propose a two-step approach to significantly improve NeRF’s performance. First, we optimize the training phase through a multi-resolution hash encoding technique, reducing the computational complexity and speeding up the learning process. Second, we accelerate the inference phase by caching the input data of the NeRF MLP, which allows for faster rendering without sacrificing quality. Our experimental results demonstrate that this approach reduces training time by 68.42% and increases inference speed by 98.18%.