PF3plat：无姿态前馈式3D Gaussian Splatting
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
AI总结：
本文提出PF3plat，一个无需相机姿态的单次前馈3DGS框架，通过预训练深度与对应模型实现粗对齐，并用轻量模块联合细化深度、姿态及几何置信度，在多项真实基准上达到最先进性能。
摘要：
我们研究在单次前馈过程中从无姿态图像进行新视角合成的问题。我们的框架利用了3DGS的快速速度、可扩展性以及高质量三维重建和视角合成能力，并在此基础上进一步扩展，以提供一种实用方案，放宽密集图像视角、精确相机姿态和大量图像重叠等常见假设。我们通过识别并解决使用像素对齐3DGS所产生的独特挑战来实现这一点：不同视角之间未对齐的3D高斯会引发噪声或稀疏梯度，从而破坏训练稳定性并阻碍收敛，尤其是在上述假设无法满足时。为缓解该问题，我们采用预训练的单目深度估计和视觉对应模型来实现3D高斯的粗对齐。随后，我们引入轻量级可学习模块，根据粗对齐结果细化深度和姿态估计，从而提高三维重建和新视角合成的质量。此外，细化后的估计被用于估计几何置信度分数，以评估3D高斯中心的可靠性，并据此对高斯参数预测进行条件化。在大规模真实世界数据集上的广泛评估表明，PF3plat在所有基准测试中均确立了新的最先进水平；全面的消融研究也验证了我们的设计选择。项目主页：https://cvlab-kaist.github.io/PF3plat/
英文摘要：
We consider the problem of novel view synthesis from unposed images in a single feed-forward. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS, where we further extend it to offer a practical solution that relaxes common assumptions such as dense image views, accurate camera poses, and substantial image overlaps. We achieve this through identifying and addressing unique challenges arising from the use of pixel-aligned 3DGS: misaligned 3D Gaussians across different views induce noisy or sparse gradients that destabilize training and hinder convergence, especially when above assumptions are not met. To mitigate this, we employ pre-trained monocular depth estimation and visual correspondence models to achieve coarse alignments of 3D Gaussians. We then introduce lightweight, learnable modules to refine depth and pose estimates from the coarse alignments, improving the quality of 3D reconstruction and novel view synthesis. Furthermore, the refined estimates are leveraged to estimate geometry confidence scores, which assess the reliability of 3D Gaussian centers and condition the prediction of Gaussian parameters accordingly. Extensive evaluations on large-scale real-world datasets demonstrate that PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. project page: https://cvlab-kaist.github.io/PF3plat/
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。
