UFV-Splatter：适应不利视角的无姿态前馈3D高斯泼溅
UFV-Splatter: Pose-Free Feed-Forward 3D Gaussian Splatting Adapted to Unfavorable Views
- NAIST, Japan（日本国家科学与技术研究所）
- Ritsumeikan University, Japan（日本立命馆大学）
- Kyoto University, Japan（京都大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出UFV-Splatter框架，通过LoRA和适配器模块，使预训练无姿态3DGS模型能处理不利视角，实验验证有效。
AI中文摘要：
本文提出了一种无姿态、前馈的3D高斯泼溅（3DGS）框架，旨在处理不利的输入视角。训练前馈方法的常见渲染设置是将3D物体置于世界原点，并从指向原点的相机进行渲染——即从有利视角渲染，这限制了这些模型在涉及变化且未知相机姿态的真实场景中的适用性。为克服此限制，我们引入了一种新颖的适应框架，使预训练的无姿态前馈3DGS模型能够处理不利视角。我们通过将重新居中的图像输入到增强有低秩适应（LoRA）层的预训练模型中，利用从有利图像中学到的先验。我们进一步提出了一个高斯适配器模块，以增强从重新居中输入导出的高斯分布的几何一致性，以及一种高斯对齐方法，用于渲染准确的训练目标视图。此外，我们引入了一种新的训练策略，利用仅由有利图像组成的现成数据集。在Google Scanned Objects数据集的合成图像和OmniObject3D数据集的真实图像上的实验结果验证了我们的方法在处理不利输入视角方面的有效性。
英文摘要：
This paper presents a pose-free, feed-forward 3D Gaussian Splatting (3DGS) framework designed to handle unfavorable input views. A common rendering setup for training feed-forward approaches places a 3D object at the world origin and renders it from cameras pointed toward the origin -- i.e., from favorable views, limiting the applicability of these models to real-world scenarios involving varying and unknown camera poses. To overcome this limitation, we introduce a novel adaptation framework that enables pretrained pose-free feed-forward 3DGS models to handle unfavorable views. We leverage priors learned from favorable images by feeding recentered images into a pretrained model augmented with low-rank adaptation (LoRA) layers. We further propose a Gaussian adapter module to enhance the geometric consistency of the Gaussians derived from the recentered inputs, along with a Gaussian alignment method to render accurate target views for training. Additionally, we introduce a new training strategy that utilizes an off-the-shelf dataset composed solely of favorable images. Experimental results on both synthetic images from the Google Scanned Objects dataset and real images from the OmniObject3D dataset validate the effectiveness of our method in handling unfavorable input views.
