Learning 3D mesh segmentation and labeling

Kalogerakis, Evangelos; Hertzmann, Aaron; Singh, Karan

doi:10.1145/1833349.1778839

Cited by 256 publications

(478 citation statements)

References 34 publications

Supporting

Mentioning

476

Contrasting

Order By: Relevance

“…They utilize part-aware shape descriptors such as concavity of the cuts [13,14], convexity [15,16] of parts, compactness [17] of parts, a shape diameter function [18], or a combination of these [19,20]. More sophisticated descriptors can be learned from a collection of shapes [21].…”

Section: Surface Segmentationmentioning

confidence: 99%

Feature-aligned segmentation using correlation clustering

et al. 2017

View full text Add to dashboard Cite

We present an algorithm for segmenting a mesh into patches whose boundaries are aligned with prominent ridge and valley lines of the shape. Our key insight is that this problem can be formulated as correlation clustering (CC), a graph partitioning problem originating from the data mining community. The formulation lends two unique advantages to our method over existing segmentation methods. First, since CC is non-parametric, our method has few parameters to tune. Second, as CC is governed by edge weights in the graph, our method offers users direct and local control over the segmentation result. Our technical contributions include the construction of the weighted graph on which CC is defined, a strategy for rapidly computing CC on this graph, and an interactive tool for editing the segmentation. Our experiments show that our method produces qualitatively better segmentations than existing methods on a wide range of inputs.

show abstract

Section: Surface Segmentationmentioning

confidence: 99%

Feature-aligned segmentation using correlation clustering

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Segmentation-based methods of 3D object recognition perform well in tidy, relatively simple environments and many state-of-the-art object recognition methods are based on pre-recognition scene segmentation [15,16,25,26,20,14]. However, these methods are limited and prone to generate errors, as initial segmentation imposes a fixed structure of the scene before any understanding takes place.…”

Section: Introduction and Related Workmentioning

confidence: 99%

“…This is an extended version of the paper presented at the 14th National Conference on Robotics (KKR 2016), Polanica Zdrój, Poland, September [14][15][16][17][18]2016 …”

mentioning

confidence: 99%

Keypoint-Less, Heuristic Application of Local 3D Descriptors

Harasymowicz-Boggio

Chechliński

2017

Foundations of Computing and Decision Sciences

View full text Add to dashboard Cite

Abstract. One of the most important topics in the research concerning 3D local descriptors is computational efficiency. The state-of-the-art approach addressing this matter consists in using keypoint detectors that effectively limit the number of points for which the descriptors are computed. However, the choice of keypoints is not trivial and might have negative implications, such as the omission of relevant areas. Instead, focusing on the task of single object detection, we propose a keypoint-less approach to attention focusing in which the full scene is processed in a hierarchical manner: weaker, less rejective and faster classification methods are used as heuristics for increasingly robust descriptors, which allows to use more demanding algorithms at the top level of the hierarchy. We have developed a massively-parallel, open source object recognition framework, which we use to explore the proposed method on demanding, realistic indoor scenes, applying the full power available in modern computers.

show abstract

“…Different approaches have been applied to achieve these goals. Classical segmentation based approaches apply generic [1,2] or specifically designed [3,4,5] methods to extract the different body parts that can be then characterized with local measurements. Accurate human body partitioning in anthropometric applications is, however, usually obtained by systems exploiting specific protocols, poses, machines, etc.…”

Section: Introductionmentioning

confidence: 99%

Robust Automatic Labelling of Anatomical Landmarks on 3D Body Scans

Giachetti

Castellani²,

Lovato³

et al. 2012

Proceedings of the 3rd International Conference on 3D Body Scanning Technologies, Lugano, Switzerland, 16-17 October 2012

View full text Add to dashboard Cite

In this paper we analyze the performance of a pipeline for the extraction and semantic labelling of geometrically salient points on acquired human body models, improving the quality of the results and discussing its robustness against pose and body type variations. Following the approach introduced in [10], we use a heat diffusion approach automatically detecting points as maxima of the autodiffusion function and using supervised classification to assign them a semantic label related to the anatomical part where the point is located. The resulting map can be used to perform measurements or to detect pose. The motivation of this approach is related to the fact that landmarks used in traditional anthropometry are not easily identified in digital models because they are localized by palpation and are not geometrically salient. An anatomical measurement system should be instead based on purely geometrical or image based landmarks. It is therefore interesting to find points of this kind that can be recognized in different subjects. The use of heat diffusion analysis enables a robust salient point detection at different levels of detail and the creation of rich point descriptors not depending only on local geometry but also on global context, invariant with respect to articulated deformations (pose variation) and sufficiently stable against changes in body type. In this work we improved our previous semantic labelling approach based on heat diffusion by selecting optimal point descriptors and feature-space distances and applying a hierarchical coarse to fine correction performing the classification at different scales and propagating the assigned labels from the coarser scale to the finer ones. Furthermore we tested the method on a collection of models representing different body types and with approximately fixed or largely different poses in order to demonstrate the robustness of the pipeline. Experimental results show that this approach can be used to recognize robustly at least a selection of landmarks on subjects with different body types and independently on pose and could therefore applied for automatic anthropometric analysis.

show abstract

Learning 3D mesh segmentation and labeling

Cited by 256 publications

References 34 publications

Feature-aligned segmentation using correlation clustering

Feature-aligned segmentation using correlation clustering

Keypoint-Less, Heuristic Application of Local 3D Descriptors

Robust Automatic Labelling of Anatomical Landmarks on 3D Body Scans

Contact Info

Product

Resources

About