DiffusionShadow：基于扩散的神经体积渲染阴影缓存

中文摘要 AI 辅助

隐式神经表示（INRs）因其紧凑性和对大规模数据集的可扩展性，在科学可视化领域获得了发展势头，使其非常适合与直接体积渲染（DVR）集成。然而，具有高级光照效果（如阴影）的INR实时体积渲染在计算上仍然昂贵，因为通过射线行进评估阴影项成本高昂。或者，为许多光照方向预计算并存储阴影在内存和存储方面都是不可行的。为了解决这个问题，我们引入了一种基于扩散的阴影缓存框架，将大量预计算的阴影INR压缩到单个扩散模型中。我们的方法不专注于泛化到未见过的方向，而是有效地在运行时记忆并重建一组密集的预训练光照条件。我们首先将一组阴影系数体积编码为阴影INR，然后训练一个以光照方向为条件的扩散模型，在推理时预测相应的阴影INR权重。这种设计直接与标准INR渲染器集成，无需额外的运行时采样。实验表明，我们的方法在绕过独立INR的庞大存储膨胀的同时，实现了比传统方法更快的渲染速度，产生的阴影与大多数参考结果非常接近。

英文摘要

Implicit neural representations (INRs) have gained momentum in scientific visualization due to their compactness and scalability to large datasets, making them well suited for integration with direct volume rendering (DVR). However, real-time volume rendering of INR with advanced illumination effects, such as shadows, remains computationally expensive, as evaluating shadow terms via ray marching is costly. Alternatively, precomputing and storing shadows for many lighting directions is prohibitive in both memory and storage. To address this, we introduce a diffusion-based shadow caching framework that compresses a vast set of pre-calculated shadow INRs into a single diffusion model. Rather than focusing on generalizing to unseen directions, our method effectively memorizes and reconstructs a dense set of pre-trained lighting conditions on the fly. We first encode a collection of shadow coefficient volumes as shadow INRs, and then train a diffusion model conditioned on lighting direction to predict the corresponding shadow INR weights at inference time. This design integrates directly with standard INR renderers without additional runtime sampling. Experiments show that our approach achieves faster rendering than traditional methods while bypassing the massive storage bloat of independent INRs, producing shadows that closely match most of the reference results.

发表机构

• University of California, Davis（加州大学戴维斯分校）
• NVIDIA（英伟达）
• Argonne National Laboratory（阿贡国家实验室）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

13 pages, 6 figures