arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.36760cs.CV
收藏

GeoGSplat:基于几何的非像素对齐高斯溅射

GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

Xi’an Jiaotong University(西安交通大学);EPFL(洛桑联邦理工学院);Horizon Robotics(地平线机器人);University of the Chinese Academy of Sciences(中国科学院大学)

Jiale Wang, Chen Zhao, Haoyang Zhang, Yanhao Wu, Fei He, Yanhu Shan, Rui Wu, Wei Ke, Tong Zhang

AI总结:

GeoGSplat是融入几何先验的非像素对齐高斯溅射模型,通过双分支编码器与分层解码器,在DTU、NRGBD数据集上优于现有方法,对大视角变化泛化能力更强。

摘要:

前馈高斯溅射可实现高效的新视图合成,但像素对齐的预测会使基元数量随图像分辨率和视图数量增长,导致大量冗余和计算成本增加。非像素对齐方法通过预测固定数量的高斯来解决此限制,但由于缺乏显式光线和深度约束,这些方法会产生错位的高斯中心,在大视角变化下引发渲染伪影。为解决该问题,我们提出GeoGSplat,这是一种基于几何的前馈模型,将几何先验显式融入非像素对齐框架。双分支编码器分别构建锚点(Anchors)和三平面(Triplane),以捕获粗略3D结构和细粒度场景特征;随后分层解码器逐步解码密集3D点和高斯基元,实现3D重建与新视图合成。GeoGSplat在DTU和NRGBD数据集的新视图合成与重建任务上,均优于当前最先进的像素对齐和非像素对齐高斯溅射方法。当目标视点远离输入相机时,我们的基于几何的范式优势进一步提升,展现出对大视角变化更强的泛化能力。项目页面:this https URL

英文摘要:

Feed-forward Gaussian Splatting enables efficient novel view synthesis, but pixel-aligned prediction makes the primitive count grow with image resolution and view count, leading to substantial redundancy and increased computational cost. Non-pixel-aligned methods address this limitation by predicting a fixed number of Gaussians. Without explicit ray and depth constraints, these methods yield misplaced Gaussian centers, causing rendering artifacts under large viewpoint changes. To address this issue, we introduce GeoGSplat, a geometry-grounded feed-forward model that explicitly incorporates geometric priors into the non-pixel-aligned framework. A dual-branch encoder constructs Anchors and Triplane to capture coarse 3D structure and fine-grained scene features, respectively. Subsequently, a hierarchical decoder progressively decodes dense 3D points and Gaussian primitives, enabling 3D reconstruction and novel view synthesis. GeoGSplat surpasses both state-of-the-art pixel-aligned and non-pixel-aligned Gaussian Splatting methods on DTU and NRGBD in terms of novel view synthesis and reconstruction. The advantage of our geometry-grounded paradigm further increases as target viewpoints move farther from the input cameras, demonstrating stronger generalization to large viewpoint changes. Project Page: https://comedy0913.github.io/projects/geogsplat

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑