Instance by Instance: An Iterative Framework for Multi-instance 3D Registration
This addresses a challenging problem in computer vision and robotics for applications like object recognition and scene understanding, representing a novel framework rather than an incremental improvement.
The paper tackles the problem of multi-instance 3D registration by proposing an iterative framework called instance-by-instance (IBI) that registers objects from easiest to hardest, continuously eliminating outliers. It achieves state-of-the-art performance with a 12.02%/12.35% higher MHF1 than the previous best method on synthetic/real datasets.
Multi-instance registration is a challenging problem in computer vision and robotics, where multiple instances of an object need to be registered in a standard coordinate system. In this work, we propose the first iterative framework called instance-by-instance (IBI) for multi-instance 3D registration (MI-3DReg). It successively registers all instances in a given scenario, starting from the easiest and progressing to more challenging ones. Throughout the iterative process, outliers are eliminated continuously, leading to an increasing inlier rate for the remaining and more challenging instances. Under the IBI framework, we further propose a sparse-to-dense-correspondence-based multi-instance registration method (IBI-S2DC) to achieve robust MI-3DReg. Experiments on the synthetic and real datasets have demonstrated the effectiveness of IBI and suggested the new state-of-the-art performance of IBI-S2DC, e.g., our MHF1 is 12.02%/12.35% higher than the existing state-of-the-art method ECC on the synthetic/real datasets.