PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections
This work addresses a fundamental problem in computer vision for applications like 3D reconstruction, though it appears incremental as it builds on existing differentiable and graph optimization techniques.
The paper tackles the challenge of robustly estimating camera poses from images, especially for small and sparse camera pose graphs, by proposing PRAGO, a differentiable method that refines rotational poses from objectness detections, achieving a 21% improvement in rotations on 7-Scenes data.
Robustly estimating camera poses from a set of images is a fundamental task which remains challenging for differentiable methods, especially in the case of small and sparse camera pose graphs. To overcome this challenge, we propose Pose-refined Rotation Averaging Graph Optimization (PRAGO). From a set of objectness detections on unordered images, our method reconstructs the rotational pose, and in turn, the absolute pose, in a differentiable manner benefiting from the optimization of a sequence of geometrical tasks. We show how our objectness pose-refinement module in PRAGO is able to refine the inherent ambiguities in pairwise relative pose estimation without removing edges and avoiding making early decisions on the viability of graph edges. PRAGO then refines the absolute rotations through iterative graph construction, reweighting the graph edges to compute the final rotational pose, which can be converted into absolute poses using translation averaging. We show that PRAGO is able to outperform non-differentiable solvers on small and sparse scenes extracted from 7-Scenes achieving a relative improvement of 21% for rotations while achieving similar translation estimates.