تقرير
SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction
| العنوان: | SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction |
|---|---|
| المؤلفون: | Lee, Yongjae, Zhang, Zhaoliang, Fan, Deliang |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | 3D Gaussian Splatting (3DGS) has made a significant stride in novel view synthesis, demonstrating top-notch rendering quality while achieving real-time rendering speed. However, the excessively large number of Gaussian primitives resulting from 3DGS' suboptimal densification process poses a major challenge, slowing down frame-per-second (FPS) and demanding considerable memory cost, making it unfavorable for low-end devices. To cope with this issue, many follow-up studies have suggested various pruning techniques, often in combination with different score functions, to optimize rendering performance. Nonetheless, a comprehensive discussion regarding their effectiveness and implications across all techniques is missing. In this paper, we first categorize 3DGS pruning techniques into two types: Cross-view pruning and pixel-wise pruning, which differ in their approaches to rank primitives. Our subsequent experiments reveal that while cross-view pruning leads to disastrous quality drops under extreme Gaussian primitives decimation, the pixel-wise pruning technique not only sustains relatively high rendering quality with minuscule performance degradation but also provides a reasonable minimum boundary for pruning. Building on this observation, we further propose multiple variations of score functions and empirically discover that the color-weighted score function outperforms others for discriminating insignificant primitives for rendering. We believe our research provides valuable insights for optimizing 3DGS pruning strategies for future works. Comment: Comprehensive experiments are in progress |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2405.17793 |
| رقم الأكسشن: | edsarx.2405.17793 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |