Multi-modal 3D Shape Reconstruction Under Calibration Uncertainty using Parametric Level Set Methods
This addresses the problem of accurate 3D modeling from noisy, multi-source data for applications like medical imaging or computer vision, representing an incremental improvement with a hybrid approach.
The paper tackles 3D shape reconstruction from multi-modal data with uncertain calibration parameters by using a parametric level set method with ellipsoidal radial basis functions, resulting in robust and scalable reconstructions that surpass traditional methods.
We consider the problem of 3D shape reconstruction from multi-modal data, given uncertain calibration parameters. Typically, 3D data modalities can be in diverse forms such as sparse point sets, volumetric slices, 2D photos and so on. To jointly process these data modalities, we exploit a parametric level set method that utilizes ellipsoidal radial basis functions. This method not only allows us to analytically and compactly represent the object, it also confers on us the ability to overcome calibration related noise that originates from inaccurate acquisition parameters. This essentially implicit regularization leads to a highly robust and scalable reconstruction, surpassing other traditional methods. In our results we first demonstrate the ability of the method to compactly represent complex objects. We then show that our reconstruction method is robust both to a small number of measurements and to noise in the acquisition parameters. Finally, we demonstrate our reconstruction abilities from diverse modalities such as volume slices obtained from liquid displacement (similar to CTscans and XRays), and visual measurements obtained from shape silhouettes.