الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Conventional 3D Gaussian Splatting (3DGS) requires depth sorting and ordered alpha blending to correctly render overlapping Gaussian primitives. Stochastic transparency enables sorting-free rendering by replacing fractional alpha contributions with discrete stochastic visibility samples, but produces substantial spatial and temporal noise at low sample counts. We refer to this conversion from continuous Gaussian splats to discrete visibility samples as \textit{Gaussian Stippling}. Based on this, we present an efficient order-independent rendering and reconstruction framework that operates directly on unmodified 3DGS assets. Our method adaptively integrates primitive-based and fragment-based stippling, leveraging their complementary strengths across different rendering regimes to significantly improve rendering throughput. To recover high-quality images from sparse stochastic samples, we further introduce a lightweight Gaussian-aware spatiotemporal reconstruction network. By exploiting the Gaussian attributes retained by each stipple, the network aggregates structured stochastic clues across both space and time, effectively suppressing stippling noise. Experiments show that our hybrid Gaussian stippling method, coupled with a spatiotemporal reconstruction network trained on diverse scenes, generalizes to unseen scenes and enables interactive, temporally stable, and visually plausible rendering on mobile devices without retraining or preprocessing. With scene-specific training and appropriately scaled sampling and network capacity, our method further outperforms the baselines in visual quality, offering a high-fidelity configuration for quality-prioritized applications.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Huang, Z., Mai, S., Zheng, C., Meng, Y., & Huo, Y. (2026). Gaussian Stippling: عرض رش غاوس ثلاثي الأبعاد الفعّال دون فرز عبر أخذ عينات هجين وإعادة بناء زمكانية. https://omanscience.com/ar/articles/gaussian-stippling-efficient-sorting-free-3d-gaussian-rendering-through-hybrid-sampling-and-spatiotemporal-reconstruction
MLA 9
Huang, Zijian, et al. "Gaussian Stippling: عرض رش غاوس ثلاثي الأبعاد الفعّال دون فرز عبر أخذ عينات هجين وإعادة بناء زمكانية." https://omanscience.com/ar/articles/gaussian-stippling-efficient-sorting-free-3d-gaussian-rendering-through-hybrid-sampling-and-spatiotemporal-reconstruction.
شيكاغو (المؤلف–التاريخ)
Huang, Zijian, Suiliang Mai, Chuankun Zheng, Yuan Meng, and Yuchi Huo. 2026. "Gaussian Stippling: عرض رش غاوس ثلاثي الأبعاد الفعّال دون فرز عبر أخذ عينات هجين وإعادة بناء زمكانية." https://omanscience.com/ar/articles/gaussian-stippling-efficient-sorting-free-3d-gaussian-rendering-through-hybrid-sampling-and-spatiotemporal-reconstruction.
هارفارد
Huang, Z., Mai, S., Zheng, C., Meng, Y. and Huo, Y. (2026) 'Gaussian Stippling: عرض رش غاوس ثلاثي الأبعاد الفعّال دون فرز عبر أخذ عينات هجين وإعادة بناء زمكانية', Available at: https://omanscience.com/ar/articles/gaussian-stippling-efficient-sorting-free-3d-gaussian-rendering-through-hybrid-sampling-and-spatiotemporal-reconstruction.
فانكوفر
Huang Z, Mai S, Zheng C, Meng Y, Huo Y. Gaussian Stippling: عرض رش غاوس ثلاثي الأبعاد الفعّال دون فرز عبر أخذ عينات هجين وإعادة بناء زمكانية. https://omanscience.com/ar/articles/gaussian-stippling-efficient-sorting-free-3d-gaussian-rendering-through-hybrid-sampling-and-spatiotemporal-reconstruction
IEEE
Z. Huang, S. Mai, C. Zheng, Y. Meng, and Y. Huo, "Gaussian Stippling: عرض رش غاوس ثلاثي الأبعاد الفعّال دون فرز عبر أخذ عينات هجين وإعادة بناء زمكانية," https://omanscience.com/ar/articles/gaussian-stippling-efficient-sorting-free-3d-gaussian-rendering-through-hybrid-sampling-and-spatiotemporal-reconstruction.