HiSplat：面向泛化稀疏视角重建的分层3D高斯泼溅
HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
AI总结：
针对现有泛化单尺度3D高斯泼溅方法重建时易出现位置偏差与伪影的问题，本文提出HiSplat分层框架，通过由粗到精生成多尺度高斯并设计跨尺度交互模块，仅用双视角输入即可提升重建质量与跨数据集泛化能力。
摘要：
从多视角重建3D场景是立体视觉中的一项基础任务。近期，泛化3D高斯泼溅技术的发展使得仅通过前馈预测逐像素高斯参数、无需额外优化，就能从稀疏输入视角为未见过的场景生成高质量的新视角合成结果。然而现有方法通常生成单尺度3D高斯，既缺乏大尺度结构表征也缺乏纹理细节表征，会导致位置偏差和伪影。本文提出了名为HiSplat的新型框架，在泛化3D高斯泼溅中引入分层机制，通过由粗到精的策略构建分层3D高斯。具体而言，HiSplat先生成大尺寸粗粒度高斯以捕捉大尺度结构，再生成细粒度高斯以增强精细纹理细节。为促进跨尺度交互，我们提出了用于高斯补偿的误差感知模块（Error Aware Module）和用于高斯修复的调制融合模块（Modulating Fusion Module）。我们的方法实现了分层表征的联合优化，仅需两张参考视角图像即可进行新视角合成。在多个数据集上的综合实验表明，与此前的单尺度方法相比，HiSplat显著提升了重建质量和跨数据集泛化能力。对应的消融实验以及对不同尺度3D高斯的分析揭示了该方法有效性背后的机制。项目主页：https://open3dvlab.github.io/HiSplat/
英文摘要：
Reconstructing 3D scenes from multiple viewpoints is a fundamental task in stereo vision. Recently, advances in generalizable 3D Gaussian Splatting have enabled high-quality novel view synthesis for unseen scenes from sparse input views by feed-forward predicting per-pixel Gaussian parameters without extra optimization. However, existing methods typically generate single-scale 3D Gaussians, which lack representation of both large-scale structure and texture details, resulting in mislocation and artefacts. In this paper, we propose a novel framework, HiSplat, which introduces a hierarchical manner in generalizable 3D Gaussian Splatting to construct hierarchical 3D Gaussians via a coarse-to-fine strategy. Specifically, HiSplat generates large coarse-grained Gaussians to capture large-scale structures, followed by fine-grained Gaussians to enhance delicate texture details. To promote inter-scale interactions, we propose an Error Aware Module for Gaussian compensation and a Modulating Fusion Module for Gaussian repair. Our method achieves joint optimization of hierarchical representations, allowing for novel view synthesis using only two-view reference images. Comprehensive experiments on various datasets demonstrate that HiSplat significantly enhances reconstruction quality and cross-dataset generalization compared to prior single-scale methods. The corresponding ablation study and analysis of different-scale 3D Gaussians reveal the mechanism behind the effectiveness. Project website: https://open3dvlab.github.io/HiSplat/
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。
