High-quality global illumination (GI) in real-time rendering is commonly achieved using precomputed lighting techniques, with lightmap as the standard choice. To support GI for static objects in dynamic lighting environments, multiple lightmaps at different lighting conditions need to be precomputed, which incurs substantial storage and memory overhead. To overcome this limitation, we propose Neural Dynamic GI (NDGI), a novel compression technique specifically designed for temporal lightmap sets. Our method utilizes multi-dimensional feature maps and lightweight neural networks to integrate the temporal information instead of storing multiple sets explicitly, which significantly reduces the storage size of lightmaps. Additionally, we introduce a block compression (BC) simulation strategy during the training process, which enables BC compression on the final generated feature maps and further improves the compression ratio. To enable efficient real-time decompression, we also integrate a virtual texturing (VT) system with our neural representation. Compared with prior methods, our approach achieves high-quality dynamic GI while maintaining remarkably low storage and memory requirements, with only modest real-time decompression overhead. To facilitate further research in this direction, we will release our temporal lightmap dataset precomputed in multiple scenes featuring diverse temporal variations.

翻译：高质量全局光照在实时渲染中通常通过预计算光照技术实现，其中光图是标准选择。为支持动态光照环境中静态物体的全局光照，需要预计算不同光照条件下的多组光图，这会导致巨大的存储和内存开销。为克服这一限制，我们提出神经动态全局光照（NDGI），一种专门针对时序光图集的新型压缩技术。该方法利用多维特征图和轻量级神经网络整合时序信息，而非显式存储多组光图，从而显著降低光图的存储体量。此外，我们在训练过程中引入块压缩（BC）模拟策略，使得最终生成的特征图可直接进行BC压缩，进一步提升压缩比。为实现高效的实时解压缩，我们还将虚拟纹理（VT）系统与神经表示相集成。与现有方法相比，我们的方法能够在保持极低存储和内存需求的同时实现高质量动态全局光照，仅需适度的实时解压缩开销。为促进该方向的进一步研究，我们将发布在多个具有多样时序变化的场景中预计算的时序光图数据集。