Multi-view registration of unordered range scans by fast correspondence propagation of multi-scale descriptors
This work addresses the challenge of accurately aligning multiple unordered 3D scans, which is crucial for applications like 3D reconstruction and computer vision, but it appears to be an incremental improvement over existing methods.
The paper tackles the problem of multi-view registration for unordered range scans by developing a global approach that uses fast correspondence propagation for pair-wise registration, reliability judgment, and model augmentation, achieving good accuracy and effectiveness on public datasets.
This paper proposes a global approach for the multi-view registration of unordered range scans. As the basis of multi-view registration, pair-wise registration is very pivotal. Therefore, we first select a good descriptor and accelerate its correspondence propagation for the pair-wise registration. Then, we design an effective rule to judge the reliability of pair-wise registration results. Subsequently, we propose a model augmentation method, which can utilize reliable results of pair-wise registration to augment the model shape. Finally, multi-view registration can be accomplished by operating the pair-wise registration and judgment, and model augmentation alternately. Experimental results on public available data sets show, that this approach can automatically achieve the multi-view registration of unordered range scans with good accuracy and effectiveness.