LucidFusion：利用任意无姿态图像重建3D高斯
LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images
AI总结：
LucidFusion提出相对坐标图与相对坐标高斯，将无姿态图像对齐到主视图并通过可微光栅化恢复一致几何，实现任意数量无姿态输入的快速稳健3D重建。
摘要：
近期的大型重建模型在从单张图像生成高质量3D物体方面取得了显著进展。然而，当前的重建方法通常依赖显式的相机姿态估计或固定视点，限制了其灵活性和实际适用性。我们将3D重建重新表述为图像到图像的转换，并引入相对坐标图（Relative Coordinate Map，RCM），在不进行姿态估计的情况下将多张无姿态图像对齐到主视图。虽然RCM简化了流程，但其缺乏全局3D监督可能导致输出存在噪声。为解决这一问题，我们提出相对坐标高斯（Relative Coordinate Gaussians，RCG）作为RCM的扩展，将每个像素的坐标视为高斯中心，并采用可微光栅化以实现一致的几何与姿态恢复。我们的LucidFusion框架能够处理任意数量的无姿态输入，在数秒内生成稳健的3D重建结果，为更灵活、无姿态的3D流程铺平了道路。
英文摘要：
Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images. However, current reconstruction methods often rely on explicit camera pose estimation or fixed viewpoints, restricting their flexibility and practical applicability. We reformulate 3D reconstruction as image-to-image translation and introduce the Relative Coordinate Map (RCM), which aligns multiple unposed images to a main view without pose estimation. While RCM simplifies the process, its lack of global 3D supervision can yield noisy outputs. To address this, we propose Relative Coordinate Gaussians (RCG) as an extension to RCM, which treats each pixel's coordinates as a Gaussian center and employs differentiable rasterization for consistent geometry and pose recovery. Our LucidFusion framework handles an arbitrary number of unposed inputs, producing robust 3D reconstructions within seconds and paving the way for more flexible, pose-free 3D pipelines.
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。
