神经动态全局光照：面向动态光照环境中时序光照图的随机访问神经压缩
Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environments
用多维特征图加轻量网络把多组时序光照图隐式整合成可随机访问的神经表示，并配合虚拟纹理实现实时解压，这套「神经表示+块压缩模拟+VT 随机访问」的组合可直接迁移到需要大容量时序数据实时读取的视觉场景（如动态环境贴图、时序辐射场缓存）。
原文依据 we propose Neural Dynamic GI (NDGI), a novel compression technique specifically designed for temporal lightmap sets
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论实时渲染中的高质量全局光照（GI）通常借助预计算光照技术实现，其中光照图是标准选择。为在动态光照环境下支持静态物体的 GI，需要预计算不同光照条件下的多张光照图，这会带来可观的存储与内存开销。为克服这一局限，我们提出神经动态全局光照（NDGI），一种专门针对时序光照图集合设计的全新压缩技术。该方法利用多维特征图与轻量神经网络来整合时序信息，而非显式存储多组光照图，从而显著降低光照图的存储规模。此外，我们在训练过程中引入块压缩（BC）模拟策略，使最终生成的特征图能够进行 BC 压缩，从而进一步提升压缩比。为实现高效的实时解压，我们还将虚拟纹理（VT）系统与神经表示相结合。与先前方法相比，本方法在保持高质量动态 GI 的同时，仅需极低的存储与内存开销，且实时解压开销适中。为促进该方向的后续研究，我们将发布在多个场景中预计算的时序光照图数据集，这些场景具有多样的时序变化。
英文原文摘要 1420 字符
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.