Region-based saliency estimation for 3D shape analysis and understanding

Abstract

This is the author accepted manuscript. The final version is available from Elsevier via http://dx.doi.org/10.1016/j.neucom.2016.01.012The detection of salient regions is an important pre-processing step for many 3D shape analysis and understanding tasks. This paper proposes a novel method for saliency detection in 3D free form shapes. Firstly, we smooth the surface normals by a bilateral filter. Such a method is capable of smoothing the surfaces and retaining the local details. Secondly, a novel method is proposed for the estimation of the saliency value of each vertex. To this end, two new features are defined: Retinex-based Importance Feature (RIF) and Relative Normal Distance (RND). They are based on the human visual perception characteristics and surface geometry respectively. Since the vertex based method cannot guarantee that the detected salient regions are semantically continuous and complete, we propose to refine such values based on surface patches. The detected saliency is finally used to guide the existing techniques for mesh simplification, interest point detection, and overlapping point cloud registration. The comparative studies based on real data from three publicly accessible databases show that the proposed method usually outperforms five selected state of the art ones both qualitatively and quantitatively for saliency detection and 3D shape analysis and understandingauthorsversionPeer reviewe

A Review on Deep Learning Approaches for 3D Data Representations in Retrieval and Classifications

“…In this method, a probability density function is defined on voxilized shape signal and the model which is a deep convolutional energybased model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC like Langevin dynamics. In the training stage, analysis by synthesis [15] is used unlike the adversarial learning on the variational inference. The same set of parameters of a single model is used for both the learning and sampling process which leads to statistically rigorous framework.…”

“…The increasing availability of 3D models from constructed and captured 3D data from low-cost acquisition devices and other modeling tools requires effective algorithms to perform key tasks such as retrieval [1]- [3], classification [4]- [7], recognition [8]- [10], and other 3D shape analysis tasks [11]- [15]. In 3D deep learning algorithm, there are two key challenges, i.e., the 3D data representation to use and the network structure adopted.…”

“…In 3D deep learning algorithm, there are two key challenges, i.e., the 3D data representation to use and the network structure adopted. Majority of the deep learning methods are deeply rooted in 2D data [15] which makes it more challenging on 3D data, fortunately with increase interest on 3D objects like the yearly 3D shape retrieval contest organized by [16] in order to evaluate the effectiveness of 3D retrieval algorithms and other 3D objects related tasks have increased tremendously the number of deep learning algorithm on different 3D data.…”

Saliency driven vasculature segmentation with infinite perimeter active contour model

“…Research on saliency detection with applications in medical imaging has not been widely exploited [48]. In this section, we review the relevant work on detecting abnormalities in different modalities of medical images by means of saliency information.…”

Point cloud saliency detection via local sparse coding

“…There are many computational methods for simulating the HVS and visual saliency, but it nonetheless remains an unexplored field because of the difficulty of designing algorithms to simulate this process [6]. As for computer graphics, while the concept of visual saliency has been widely explored for mesh saliency [6], [8][9][10][11][12][13][14][15][16][17][18], few studies have explored visual saliency in point clouds [19][20][21][22]. Visual saliency is an important topic for 3D surface study and has important applications in 3D geometry processing such as resizing [1], simplification [23][24], smoothing [25], segmentation [26], shape matching and retrieval [27][28], 3D printing [29], and so forth.…”