Beyond Complete Shapes: A Quantitative Evaluation of 3D Shape Matching Algorithms
This addresses a practical challenge in computer vision and graphics for researchers and practitioners working with incomplete 3D data, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of matching partially observed 3D shapes, which is underexplored due to limited and unrealistic datasets, by introducing a framework for generating infinite partial shape matching instances from existing complete datasets and creating a benchmark with 2543 shapes to evaluate state-of-the-art methods.
Finding correspondences between 3D shapes is an important and long-standing problem in computer vision, graphics and beyond. While approaches based on machine learning dominate modern 3D shape matching, almost all existing (learning-based) methods require that at least one of the involved shapes is complete. In contrast, the most challenging and arguably most practically relevant setting of matching partially observed shapes, is currently underexplored. One important factor is that existing datasets contain only a small number of shapes (typically below 100), which are unable to serve data-hungry machine learning approaches, particularly in the unsupervised regime. In addition, the type of partiality present in existing datasets is often artificial and far from realistic. To address these limitations and to encourage research on these relevant settings, we provide a generic and flexible framework for the procedural generation of challenging partial shape matching scenarios. Our framework allows for a virtually infinite generation of partial shape matching instances from a finite set of shapes with complete geometry. Further, we manually create cross-dataset correspondences between seven existing (complete geometry) shape matching datasets, leading to a total of 2543 shapes. Based on this, we propose several challenging partial benchmark settings, for which we evaluate respective state-of-the-art methods as baselines.