无需已知相机参数，快速重建真实场景3D高斯点云并控制光照外观。
WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images
- 端到端训练，联合学习3D高斯与图像条件外观嵌入
- 单秒内完成稀疏视图下3D高斯重建，支持多光照条件变化
- 适用于无约束照片集，适合真实世界应用
我们提出WildSplatter，一种面向未知相机参数和复杂光照条件下无约束图像的前馈式3D高斯点阵（3DGS）模型。3DGS是一种高效的场景表示方法，可实现高质量实时渲染；然而，传统方法通常需要迭代优化，并依赖多视角、光照一致且相机参数已知的图像。WildSplatter在无约束照片集合上进行训练，联合学习3D高斯与基于输入图像的外观嵌入，从而灵活调节高斯颜色以应对显著的光照与外观变化。该方法可在不到1秒内从稀疏输入视图重建3D高斯，并支持在不同光照条件下进行外观控制。实验表明，在光照变化剧烈的真实数据集上，本方法优于现有无位姿3DGS方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。