Mesh segmentation based on curvatures using the GPU

Lee, Jung; Kim, Seokhun; Kim, Sun-Jeong

doi:10.1007/s11042-014-2104-1

Cited by 14 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is while 3D gradient enhancement is limited to correlating the specular material to surface features variations, which are illustrated in the red and green squares of Fig 18-b. Toon shading style often tends to mask subtle shading variations due to the quantization of the reflected lighting intensity. This limitation clearly appears in Fig 19-a which shows the depiction of the hand 3D model using toon shading style based on [16] technique. Observe how their technique is unable to depict the wrinkles that often appear on the hand.…”

Section: Qualitative Comparisons With Previous Methodsmentioning

confidence: 99%

“…It then makes use of locally consistent lights for improving shape perception. Also, Lee et al [16] proposed an algorithm for mesh segmentation considers curvatures and uses the GPU to improve the rendering time. This algorithm can also be effective in enhancing the stylized depiction.…”

Section: Related Workmentioning

confidence: 99%

“…We asked the participants to choose the best image in Fig. 19: Comparison with the technique proposed by Lee et al [16]. (a) Toon shading style enhanced using [16].…”

Section: User Studymentioning

confidence: 99%

“…19: Comparison with the technique proposed by Lee et al [16]. (a) Toon shading style enhanced using [16]. (b) Toon shading style enhanced using Geometry-based shading technique.…”

Section: User Studymentioning

confidence: 99%

See 3 more Smart Citations

Geometry-based shading for shape depiction enhancement

Al-Rousan

Sunar

Kolivand

2017

Multimed Tools Appl

View full text Add to dashboard Cite

Recent works on Non-Photorealistic Rendering (NPR) show that object shape enhancement requires sophisticated effects such as: surface details detection and stylized shading. To date, some rendering techniques have been proposed to overcome this issue, but most of which are limited to correlate shape enhancement functionalities to surface feature variations. Therefore, this problem still persists especially in NPR. This paper is an attempt to address this problem by presenting a new approach for enhancing shape depiction of 3D objects in NPR. We first introduce a tweakable shape descriptor that offers versatile functionalities for describing the salient features of 3D objects. Then to enhance the classical shading models, we propose a new technique called Geometry-based Shading. This technique controls reflected lighting intensities based on local geometry. Our approach works without any constraint on the choice of material or illumination. We demonstrate results obtained with Blinn-Phong shading, Gooch shading, and cartoon shading. These results prove that our approach produces more satisfying results compared with the results of previous shape depiction techniques. Finally, our approach runs on modern graphics hardware in real time, which works efficiently with interactive 3D visualization.

show abstract

Section: Qualitative Comparisons With Previous Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…We asked the participants to choose the best image in Fig. 19: Comparison with the technique proposed by Lee et al [16]. (a) Toon shading style enhanced using [16].…”

Section: User Studymentioning

confidence: 99%

“…19: Comparison with the technique proposed by Lee et al [16]. (a) Toon shading style enhanced using [16]. (b) Toon shading style enhanced using Geometry-based shading technique.…”

Section: User Studymentioning

confidence: 99%

See 2 more Smart Citations

Geometry-based shading for shape depiction enhancement

Al-Rousan

Sunar

Kolivand

2017

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…The modes are the roots of the resulting subtrees. This algorithm was used notably in the context of superpixels [VS08], for curvature‐based mesh segmentation [LKK15] and is very well suited to the GPU [FS10]. We propose to adapt this algorithm to use filtered quadrics , in order to produce a superpixel‐like clustering of 3D surfaces.…”

Section: Introductionmentioning

confidence: 99%

Filtered Quadrics for High‐Speed Geometry Smoothing and Clustering

Legrand

Thiery

Boubekeur

2019

Computer Graphics Forum

View full text Add to dashboard Cite

Modern 3D capture pipelines produce dense surface meshes at high speed, which challenge geometric operators to process such massive data on‐the‐fly. In particular, aiming at instantaneous feature‐preserving smoothing and clustering disqualifies global variational optimizers and one usually relies on high‐performance parallel kernels based on simple measures performed on the positions and normal vectors associated with the surface vertices. Although these operators are effective on small supports, they fail at properly capturing larger scale surface structures. To cope with this problem, we propose to enrich the surface representation with filtered quadrics, a compact and discriminating range space to guide processing. Compared to normal‐based approaches, this additional vertex attribute significantly improves feature preservation for fast bilateral filtering and mode‐seeking clustering, while exhibiting a linear memory cost in the number of vertices and retaining the simplicity of convolutional filters. In particular, the overall performance of our approach stems from its natural compatibility with modern fine‐grained parallel computing architectures such as graphics processor units (GPU). As a result, filtered quadrics offer a superior ability to handle a broad spectrum of frequencies and preserve large salient structures, delivering meshes on‐the‐fly for interactive and streaming applications, as well as quickly processing large data collections, instrumental in learning‐based geometry analysis.

show abstract

Curvature determination in range images: new methods and comparison study

Hauenstein

Newman

2018

Multimed Tools Appl

View full text Add to dashboard Cite

Mesh segmentation based on curvatures using the GPU

Cited by 14 publications

References 13 publications

Geometry-based shading for shape depiction enhancement

Geometry-based shading for shape depiction enhancement

Filtered Quadrics for High‐Speed Geometry Smoothing and Clustering

Curvature determination in range images: new methods and comparison study

Contact Info

Product

Resources

About