A Study of Shape Modeling Against Noise
This addresses a fundamental but understudied problem in shape modeling for computer vision and medical imaging applications, though it appears incremental as it focuses on evaluation and noise definition rather than a new method.
The paper tackled the problem of shape denoising, which involves handling shapes with missing pieces or outliers, by introducing six types of noise and an objective measure for noise level, and evaluated seven methods, including six deep learning approaches, for their denoising capabilities.
Shape modeling is a challenging task with many potential applications in computer vision and medical imaging. There are many shape modeling methods in the literature, each with its advantages and applications. However, many shape modeling methods have difficulties handling shapes that have missing pieces or outliers. In this regard, this paper introduces shape denoising, a fundamental problem in shape modeling that lies at the core of many computer vision and medical imaging applications and has not received enough attention in the literature. The paper introduces six types of noise that can be used to perturb shapes as well as an objective measure for the noise level and for comparing methods on their shape denoising capabilities. Finally, the paper evaluates seven methods capable of accomplishing this task, of which six are based on deep learning, including some generative models.