DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes

Matveev, Albert; Rakhimov, Ruslan; Artemov, Alexey; Bobrovskikh, Gleb; Egiazarian, Vage; Bogomolov, Emil; Panozzo, Daniele; Zorin, Denis; Burnaev, Evgeny

doi:10.48550/arxiv.2011.15081

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of the approaches mentioned above, similarly to analytical methods, perform per-point classification. Recently, a new approach to sharp feature lines detection has occurred in DEF [15] that can represent features with so-called distance fields. Our pipeline is based upon this paper since it provides a soft detection suitable for curve inference precisely on edge.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

3D Parametric Wireframe Extraction Based on Distance Fields

Matveev,

Artemov,

Zorin

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fig. 1. Parametric wireframe extraction pipeline: (a) -dense point cloud with estimated distance field, (b) -sharp point skeleton with color-coded segmentation into individual curves (note the black clusters corresponding to the detected corner neighborhoods), (c) -optimized topological graph with final corner points (red), (d) -extracted parametric wireframe, (e) -ground-truth parametric wireframe.We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.CCS Concepts: • Computing methodologies → Parametric curve and surface models; Point-based models.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Recently, a new approach to sharp feature lines detection has occurred -Deep Feature Estimators (DEFs) [15]. In DEF, the authors introduced a novel learning-based framework to infer sharp feature curves in unordered 3D point clouds.…”

Section: Introductionmentioning

confidence: 99%

3D Parametric Wireframe Extraction Based on Distance Fields

Matveev,

Artemov,

Zorin

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes

Cited by 1 publication

References 0 publications

3D Parametric Wireframe Extraction Based on Distance Fields

3D Parametric Wireframe Extraction Based on Distance Fields

Contact Info

Product

Resources

About