用神经网络实现实时光晕效果，速度比现有方法快12%至28%。
Neural Bloom: A Deep Learning Approach to Real-Time Lighting
- 用两个神经网络模型直接生成亮度掩码，替代传统多步模糊和采样操作。
- FastNBL比当前最优方法快28%，NBL快12%，且保持高质量光晕效果。
- 适合需要高帧率、低延迟的实时渲染场景，如游戏与VR应用。
我们提出一种基于神经网络的实时光晕效果生成新方法。该方法从3D场景视图中生成亮度掩码，速度比现有最优方法快最多30%。传统技术依赖多步模糊与纹理采样，常含条件分支，执行开销大。本文提出两种神经网络方案：神经光晕照明（NBL）与快速神经光晕照明（FastNBL），重点优化质量和性能。在多种3D场景上测试，评估了亮度掩码精度与推理速度。结果表明，两种方法均在保持高质量光晕效果的同时超越标准最优实现，其中FastNBL提速28%，NBL提速12%。这一进展显著提升实时渲染中的光影真实感，减少计算资源消耗，有助于维持高帧率环境下的沉浸体验与流畅性。
原文摘要 · Abstract (English)
We propose a novel method to generate bloom lighting effect in real time using neural networks. Our solution generate brightness mask from given 3D scene view up to 30% faster than state-of-the-art methods. The existing traditional techniques rely on multiple blur appliances and texture sampling, also very often have existing conditional branching in its implementation. These operations occupy big portion of the execution time. We solve this problem by proposing two neural network-based bloom lighting methods, Neural Bloom Lighting (NBL) and Fast Neural Bloom Lighting (FastNBL), focusing on their quality and performance. Both methods were tested on a variety of 3D scenes, with evaluations conducted on brightness mask accuracy and inference speed. The main contribution of this work is that both methods produce high-quality bloom effects while outperforming the standard state-of-the-art bloom implementation, with FastNBL being faster by 28% and NBL faster by 12%. These findings highlight that we can achieve realistic bloom lighting phenomena faster, moving us towards more realism in real-time environments in the future. This improvement saves computational resources, which is a major bottleneck in real-time rendering. Furthermore, it is crucial for sustaining immersion and ensuring smooth experiences in high FPS environments, while maintaining high-quality realism.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。