WildSplatter: 无约束图像中基于馈送的3D高斯散射与外观控制
WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images
- NAIST（名古屋大学信息科学研究所）
- Ritsumeikan University（立命馆大学）
- Kyoto University（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WildSplatter，一种无需姿态信息的3D高斯散射模型，通过无约束图像学习3D高斯和外观嵌入，实现快速重建和光照变化下的外观控制。
AI中文摘要：
我们提出WildSplatter，一种针对无约束图像的馈送式3D高斯散射（3DGS）模型，适用于未知相机参数和变化光照条件。3DGS是一种有效的场景表示，能够实现高质量的实时渲染；然而，它通常需要迭代优化和多视角图像在一致光照下拍摄。WildSplatter在无约束照片集合上训练，并联合学习3D高斯和外观嵌入，这些嵌入基于输入图像。这种设计使高斯颜色能够灵活调节以表示显著的光照和外观变化。我们的方法在不到1秒内从稀疏输入视角重建3D高斯，并在多样的光照条件下实现外观控制。实验结果表明，我们的方法在具有变化照明的挑战性真实世界数据集上优于现有的姿态无关3DGS方法。
英文摘要：
We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requires iterative optimization and multi-view images captured under consistent lighting with known camera parameters. WildSplatter is trained on unconstrained photo collections and jointly learns 3D Gaussians and appearance embeddings conditioned on input images. This design enables flexible modulation of Gaussian colors to represent significant variations in lighting and appearance. Our method reconstructs 3D Gaussians from sparse input views in under one second, while also enabling appearance control under diverse lighting conditions. Experimental results demonstrate that our approach outperforms existing pose-free 3DGS methods on challenging real-world datasets with varying illumination.
