RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges
This provides a systematic evaluation framework for computer vision researchers working on camera pose estimation, though it is incremental as it builds on existing benchmarks and methods.
The authors tackled the problem of limited insight into image matching method limitations across geometric challenges by introducing RUBIK, a structured benchmark that systematically evaluates 14 methods across 33 difficulty levels. Their evaluation revealed that while detector-free approaches achieve the best performance (>47% success rate), they have high computational overhead, and even the top method succeeds on only 54.8% of image pairs.
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.