发表机构
Inspatio（Inspatio）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
QuerySplat是解耦3DGS几何与外观表示的前馈框架，通过双分支解码器缓解模糊问题，在DL3DV基准上实现SOTA新视图合成，PSNR较基线显著提升。
AI 中文摘要
尽管前馈三维高斯溅射（3DGS）能实现高效的三维重建，但实现高保真渲染仍具挑战性。现有像素对齐方法存在空间灵活性不足、结构冗余量大的问题，而基于查询的方法缺乏三维先验，且将几何与外观纠缠，导致模糊、依赖姿态的结果。为克服这些缺陷，我们提出QuerySplat，一种由几何先验和显式外观解耦驱动的前馈3DGS框架。具体而言，我们设计了双分支基于查询的解码器：几何分支利用预训练的视觉几何模型进行空间理解，这从本质上赋予QuerySplat无姿态建模能力；外观分支通过与几何属性回归分离的专用路径恢复高频细节。大量实验表明，QuerySplat缓解了早期基于查询的模型的模糊渲染问题，且在渲染保真度上始终优于像素对齐方法。在具有挑战性的DL3DV基准上，它实现了最先进的新视图合成性能，与最佳无姿态和需姿态的基线相比，平均峰值信噪比（PSNR）分别提升2.30 dB和1.04 dB。项目页面：this https URL。
英文摘要
While feed-forward 3D Gaussian Splatting (3DGS) enables efficient 3D reconstruction, achieving high-fidelity rendering remains challenging. Existing pixel-aligned approaches suffer from spatial inflexibility and massive structural redundancy, whereas query-based methods lack 3D priors and entangle geometry with appearance, yielding blurry, pose-dependent results. To overcome these deficiencies, we propose \textbf{QuerySplat}, a feed-forward 3DGS framework driven by geometric priors and explicit appearance decoupling. Specifically, we design a dual-branch query-based decoder: the geometry branch leverages a pretrained Vision Geometric Model for spatial understanding, which intrinsically endows QuerySplat with pose-free modeling capabilities, while the appearance branch recovers high-frequency details through a dedicated pathway separated from geometric attribute regression. Extensive experiments demonstrate that QuerySplat mitigates the blurry rendering issues of early query-based models and consistently outperforms pixel-aligned approaches in rendering fidelity. On the challenging DL3DV benchmark, it achieves state-of-the-art novel view synthesis performance, with average PSNR gains of 2.30 dB and 1.04 dB over the best pose-free and pose-required baselines, respectively. Project Page: https://inspatio.github.io/querysplat.
