Problem
Research questions and friction points this paper is trying to address.
camera pose estimation
translation directions
viewing graph consistency
global structure-from-motion
TriDE: Triangle-Consistent Translation Directions for Global Camera Pose Estimation
🤖 AI Summary
This work addresses the challenge of inconsistent pairwise translation direction estimates in global structure-from-motion, where locally plausible solutions often fail to satisfy global consistency. To resolve this, the authors propose a joint optimization framework grounded in camera triangle consistency constraints. By leveraging a graph message-passing mechanism, high-order verification signals are propagated between weighted triangles and translation directions, enabling robust, cooperative refinement of all pairwise directions while circumventing the sensitivity to initialization inherent in conventional nonlinear optimization. Theoretical analysis establishes a phase transition boundary for exact recovery under a random noise model. Experiments demonstrate that the method significantly improves translation direction estimation accuracy on real image data and consequently enhances downstream camera position reconstruction.
📝 Abstract
Pairwise translation directions are a key input to camera location estimation in global structure-from-motion. Existing estimators usually process each image pair independently, producing directions that may be locally plausible but inconsistent with the other relative directions in the viewing graph. To jointly estimate the direction, we propose TriDE, which exploits camera-triangle consistency as an efficient higher-order verification signal. Instead of solving a costly global nonlinear optimization problem that is sensitive to initialization, TriDE refines unreliable pairwise directions through message passing between directions and their incident weighted triangles. This information propagation strategy enables us to establish a strong phase-transition bound for exact recovery under a realistic random corruption model. Experiments on real image graphs show that TriDE improves direction accuracy by a large margin and yields better downstream camera locations, providing a practical link between local pairwise estimation and global camera pose geometry.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Triangle Consistency
Global Camera Pose Estimation
Message Passing
Structure-from-Motion
Phase Transition
🔎 Similar Papers
No similar papers found.
