Problem
Research questions and friction points this paper is trying to address.
Enhance accuracy and robustness in rotation averaging methods
Develop task-specific reference for rotation alignment
Evaluate performance on 1DSfM dataset
Incremental Rotation Averaging Revisited and More: A New Rotation Averaging Benchmark
🤖 AI Summary
To address large local-to-global alignment errors and poor robustness in incremental rotation averaging, this paper proposes IRAv4—a novel method that introduces a task-specific Connected Dominating Set (CDS) as a dynamically evolving, high-precision reference for rotation alignment. Crucially, IRAv4 jointly optimizes the CDS structure and the absolute rotations of its vertices via synchronized incremental estimation. By integrating incremental graph optimization with adaptive CDS construction, it avoids error accumulation inherent in conventional fixed-reference approaches. Experiments on the 1DSfM benchmark demonstrate that IRAv4 significantly improves rotation averaging accuracy—reducing mean angular error by 28.6%—and enhances robustness against outliers, maintaining stable performance even with 30% corrupted edges. These results validate the effectiveness and advancement of the CDS-driven reference construction paradigm for incremental Structure-from-Motion.
📝 Abstract
In order to further advance the accuracy and robustness of the incremental parameter estimation-based rotation averaging methods, in this paper, a new member of the Incremental Rotation Averaging (IRA) family is introduced, which is termed as IRAv4. As its most significant feature, a task-specific connected dominating set is extracted in IRAv4 to serve as a more reliable and accurate reference for rotation local-to-global alignment. This alignment reference is incrementally constructed, together with the absolute rotations of the vertices belong to it simultaneously estimated. Comprehensive evaluations are performed on the 1DSfM dataset, by which the effectiveness of both the reference construction method and the entire rotation averaging pipeline proposed in this paper is demonstrated.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Introduced IRAv4 for enhanced rotation averaging
Used task-specific connected dominating set
Incrementally constructed alignment reference
🔎 Similar Papers
No similar papers found.
