论文标题
Associative3D：稀疏视图的体积重建
Associative3D: Volumetric Reconstruction from Sparse Views
论文作者
论文摘要
本文研究了带有未知相机的场景的两个视图中3D体积重建的问题。尽管对于人类来说似乎很容易，但这个问题对计算机构成了许多挑战，因为它需要同时重建两个视图中的对象，同时还可以弄清楚它们的关系。我们提出了一种新方法，以估计重建，相机/对象/相机/相机转换上的分布以及一个Inter-View对象亲和力矩阵。然后将这些信息共同推定，以产生最有可能的场景解释。我们在室内场景的数据集上训练和测试我们的方法，并严格评估我们的联合推理方法的优点。我们的实验表明，它能够从稀疏视图中恢复合理的场景，而问题仍然具有挑战性。项目站点：https：//jasonqsy.github.io/associative3d
This paper studies the problem of 3D volumetric reconstruction from two views of a scene with an unknown camera. While seemingly easy for humans, this problem poses many challenges for computers since it requires simultaneously reconstructing objects in the two views while also figuring out their relationship. We propose a new approach that estimates reconstructions, distributions over the camera/object and camera/camera transformations, as well as an inter-view object affinity matrix. This information is then jointly reasoned over to produce the most likely explanation of the scene. We train and test our approach on a dataset of indoor scenes, and rigorously evaluate the merits of our joint reasoning approach. Our experiments show that it is able to recover reasonable scenes from sparse views, while the problem is still challenging. Project site: https://jasonqsy.github.io/Associative3D
