2025/02/27 by Thibaut Loiseau, Guillaume Bourmaud, Loiseau, Thibaut +1 · 3 voices · 4 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Benchmark (surveying) #Feature matching #Image (mathematics) #Matching (statistics) #Overhead (engineering) #Robot Manipulation and Learning #Robotics and Sensor-Based Localization #Scale (ratio) #cs.CV
paper · pdf · doi:10.48550/arxiv.2502.19955
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/02/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Camera pose estimation is crucial for many computer vision applications, yet existing benchmarks offer limited insight into method limitations across different geometric challenges. We introduce RUBIK, a novel benchmark that systematically evaluates image matching methods across well-defined geometric difficulty levels. Using three complementary criteria - overlap, scale ratio, and viewpoint angle - we organize 16.5K image pairs from nuScenes into 33 difficulty levels. Our comprehensive evaluation of 14 methods reveals that while recent detector-free approaches achieve the best performance (>47% success rate), they come with significant computational overhead compared to detector-based methods (150-600ms vs. 40-70ms). Even the best performing method succeeds on only 54.8% of the pairs, highlighting substantial room for improvement, particularly in challenging scenarios combining low overlap, large scale differences, and extreme viewpoint changes. Benchmark will be made publicly available.