Kern, RenéBrüll, FelixGrosch, ThorstenWang, BeibeiWilkie, Alexander2025-06-202025-06-2020251467-8659https://doi.org/10.1111/cgf.70178https://diglib.eg.org/handle/10.1111/cgf70178Rendering shadows for semi-transparent objects like smoke significantly enhances the realism of the final image. With advancements in ray tracing hardware, tracing visibility rays in real time has become possible. However, generating shadows for semi-transparent objects requires evaluating multiple or all intersections along the ray, resulting in a deep shadow ray. Deep Shadow Maps (DSM) offer an alternative but are constrained by their fixed resolution. We introduce Importance Deep Shadow Maps (IDSM), a real-time algorithm that adaptively distributes Deep Shadow samples based on importance captured from the current camera viewport. Additionally, we propose a novel DSM data structure built on the ray tracing acceleration structure, improving performance for scenarios requiring many samples per DSM texel. Our IDSM approach achieves speedups of up to ×6.89 compared to hardware ray tracing while maintaining a nearly indistinguishable quality level.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Visibility; Ray tracingComputing methodologies → VisibilityRay tracing10.1111/cgf.7017812 pages