论文标题
稀疏：稀疏视图摄像头姿势回归和改进
SparsePose: Sparse-View Camera Pose Regression and Refinement
论文作者
论文摘要
相机姿势估计是标准3D重建管道中的关键步骤，该管道在单个对象或场景的一组密集图像上运行。但是，姿势估计的方法通常只有几个图像可用，因为它们依赖于图像对之间可靠识别和匹配视觉特征的能力。虽然这些方法可以与密集的相机视图稳健地工作，但捕获大量图像可能是耗时或不切实际的。我们提出了稀疏的稀疏相机姿势的稀疏，给定了一组稀疏的宽基线图像（少于10）。该方法学会回归初始相机摆姿势，然后在大规模的对象数据集上训练后（CO3D：3D中的常见对象）在训练之后迭代地完善它们。在恢复准确的相机旋转和翻译方面，稀疏量显着优于常规和基于学习的基线。我们还仅使用5-9个对象的图像来证明高保真3D重建的管道。
Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation often fail when only a few images are available because they rely on the ability to robustly identify and match visual features between image pairs. While these methods can work robustly with dense camera views, capturing a large set of images can be time-consuming or impractical. We propose SparsePose for recovering accurate camera poses given a sparse set of wide-baseline images (fewer than 10). The method learns to regress initial camera poses and then iteratively refine them after training on a large-scale dataset of objects (Co3D: Common Objects in 3D). SparsePose significantly outperforms conventional and learning-based baselines in recovering accurate camera rotations and translations. We also demonstrate our pipeline for high-fidelity 3D reconstruction using only 5-9 images of an object.
