研究人员开发了 Budgeted-GS，这是一种新颖的后处理方法，旨在实现大规模 3D 高斯喷绘模型（如城市规模环境）在消费级 GPU 上的实时渲染。该技术将训练好的模型分解为多分辨率层次结构，从而可以根据可用内存动态选择细节级别。此外，Budgeted-GS 采用以预算为中心的方法进行训练，直接优化场景所需的图元数量，避免在冗余元素上浪费精力。该方法已在各种场景中得到验证，证明了在标准硬件上实现高质量实时渲染的能力。 AI
影响 使消费级硬件能够实时渲染大规模 3D 场景，可能对 AR/VR 和游戏产生影响。
排序理由 详细介绍一种新的 3D 高斯喷绘方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.07958v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across many scenes. Its quality, however, degrades sharply as the number of input image…
arXiv:2610.08756v1 Announce Type: new Abstract: The same Gaussian of a 3D Gaussian Splatting model is seen from many views, and these views do not always agree on the class it belongs to. The Gaussian may be occluded in some of them, and the confidence of the detector is not the …
arXiv:2604.09045v2 Announce Type: replace Abstract: Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level 3D segmentation. However, the supervision signals from foundation models are not…
arXiv:2610.04007v2 Announce Type: replace Abstract: We present VolS-GS, a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time (OLAT) captures and renders them under novel lighting and viewpoints. Relightable Gaussian Splatting methods typic…
arXiv:2610.03162v1 Announce Type: cross Abstract: 3D Gaussian Splatting achieves excellent visual quality with real-time rendering, but at the scale of entire cities it does not fit: a trained model carries millions of primitives and gigabytes of memory, and real-time rendering a…