arXiv cs.AI· Prakhar Kaushik, Soumava Paul, Alan Yuille·· 13 小时前AI 评分29
Hexels：用于高效场景渲染与重建的紧凑六边形图元
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
AI 导读
研究者提出 Hexels——带一阶空间颜色场的平面六边形表面图元，用更少更大的图元表示局部平面区域。在 34 个场景上，Hexels 相比内存匹配的 2DGS 将 PSNR 提升 4.53-7.38 dB，且训练显存更低；单图元对比最高提升 4.74 dB，FPS 快 2.31 倍。
正文 · 原文
Abstract:Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for efficient 3D scene and 2D image representation. Hexels exploit locally planar regions with smoothly varying appearance using fewer, larger primitives. Their hexagonal support provides an area- and boundary-efficient domain, while the local color field captures appearance variation within each primitive. Across 34 scenes, Hexels improve PSNR over memory-matched 2DGS by 4.53-7.38 dB across datasets while requiring lower training VRAM. We further ablate Hexels by showing that per primitive, Hexels outperform 2DGS by upto 4.74 dB while using lower training VRAM and having 2.31 times faster FPS. Even in unconstrained settings, Hexels offers complementary quality-memory trade-offs. For efficient 3D surface reconstruction, Hexels reduce error by 28.9% compared with memory-matched 2DGS across 15 DTU scans. On 6 Tanks and Temples surface scenes, Hexels achieves the highest mean F1 among compared methods (34.38%, versus 31.72% for 2DGS). We further also show that Hexels, as a general primitive, improves 2D image representation over Image-GS. Hexels push the Pareto frontier on the quality-efficiency trade-off of surface-aligned primitives.
| Comments: | Project page at this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.37668 [cs.CV] |
| (or arXiv:2610.37668v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37668 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Prakhar Kaushik [view email]
[v1]
Tue, 27 Oct 2026 17:59:59 UTC (36,891 KB)
来源：arXiv cs.AI · arxiv.org