GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection
This work provides a domain-specific tool for researchers in robotics and computer vision to improve robustness in visual SLAM by benchmarking geometric verification methods, though it is incremental as it builds on existing feature matching techniques.
The paper introduces GV-Bench, a benchmark for evaluating local feature matching methods in geometric verification of loop closure detection in visual SLAM, addressing long-term conditional variations, and assesses six representative methods to analyze limitations and guide future work.
Visual loop closure detection is an important module in visual simultaneous localization and mapping (SLAM), which associates current camera observation with previously visited places. Loop closures correct drifts in trajectory estimation to build a globally consistent map. However, a false loop closure can be fatal, so verification is required as an additional step to ensure robustness by rejecting the false positive loops. Geometric verification has been a well-acknowledged solution that leverages spatial clues provided by local feature matching to find true positives. Existing feature matching methods focus on homography and pose estimation in long-term visual localization, lacking references for geometric verification. To fill the gap, this paper proposes a unified benchmark targeting geometric verification of loop closure detection under long-term conditional variations. Furthermore, we evaluate six representative local feature matching methods (handcrafted and learning-based) under the benchmark, with in-depth analysis for limitations and future directions.