用神经网络动态选光，提升复杂场景渲染效率。
Neural Importance Sampling of Many Lights
- 神经网络根据局部信息预测最优选光分布
- 在多光源场景中显著降低采样方差，提升渲染质量
- 适合高复杂度场景的实时或高质量渲染应用
我们提出一种神经方法，用于估计空间变化的光选择分布，以改进蒙特卡洛渲染中的重要性采样，尤其适用于包含大量光源的复杂场景。该方法利用神经网络基于局部信息预测每个着色点的光选择分布，并通过在线方式最小化学习分布与目标分布之间的KL散度进行训练。为高效处理数百甚至上千个光源，我们将神经方法与光层次结构技术结合，使网络预测簇级分布，而现有方法在簇内采样光源。此外，引入残差学习策略，利用现有技术的初始分布加速训练收敛。该方法在多样且具有挑战性的场景中均表现出优越性能。
原文摘要 · Abstract (English)
We propose a neural approach for estimating spatially varying light selection distributions to improve importance sampling in Monte Carlo rendering, particularly for complex scenes with many light sources. Our method uses a neural network to predict the light selection distribution at each shading point based on local information, trained by minimizing the KL-divergence between the learned and target distributions in an online manner. To efficiently manage hundreds or thousands of lights, we integrate our neural approach with light hierarchy techniques, where the network predicts cluster-level distributions and existing methods sample lights within clusters. Additionally, we introduce a residual learning strategy that leverages initial distributions from existing techniques, accelerating convergence during training. Our method achieves superior performance across diverse and challenging scenes.
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。