Associative3D: Volumetric Reconstruction from Sparse Views
This addresses a challenging computer vision problem for 3D reconstruction from limited data, but it appears incremental as it builds on existing methods for sparse view reconstruction.
The paper tackles the problem of 3D volumetric reconstruction from two sparse views with unknown cameras by proposing a joint reasoning approach that estimates reconstructions, transformations, and an affinity matrix, and shows it can recover reasonable scenes from sparse views, though the problem remains challenging.
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