Part-based data-driven 3D shape interpolation

Date

2021-07-01

Author

Aydinlilar, Melike
Sahillioğlu, Yusuf

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

242
views

0
downloads

An active problem in digital geometry processing is shape interpolation which aims to generate a continuous sequence of in-betweens for a given source and target shape. Unlike traditional approaches that interpolate source and target shapes in isolation, recent data-driven approaches utilize multiple interpolations through intermediate database shapes, and consequently perform better at the expense of a database requirement. In contrast to the existing data-driven approaches that consider intermediate shapes as full inseparable entities, our novel data-driven method treats the shapes as separable parts. In particular, we interpolate parts over different intermediate shapes and merge them all in the end, which brings more flexibility and variety than the existing ways of interpolating the full shape as a whole over one fixed set of intermediates. To be able to proceed consistently over different sets of intermediate shapes, we construct a unified framework based on parametric curves. We justify the two key points in the proposed method, interpolating parts separately and data-driven by curve parameterization, in the qualitative and quantitative evaluations. We demonstrate promising results in comparison with five other techniques. Our method morphs not only poses but also forms, e.g., turning one person to another. The results are improved further with a mild data augmentation procedure that is based on the original algorithm. As a side contribution, we provide a public articulated hand dataset with fixed connectivity, which can be used in the evaluation of other interpolation methods. (C) 2021 Elsevier Ltd. All rights reserved.

Subject Keywords

3D shape interpolation, 3D shape morphing, Part-based, Data-driven

URI

https://hdl.handle.net/11511/90690

Journal

COMPUTER-AIDED DESIGN

DOI

https://doi.org/10.1016/j.cad.2021.103027

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Part-based data-driven shape interpolation Aydınlılar, Melike; Sahillioğlu, Yusuf; Department of Computer Engineering (2018) An active problem in digital geometry processing is shape interpolation which aims to generate a continuous sequence of in-betweens for a given source and target shape. Unlike traditional approaches that interpolate source and target shapes in isolation, recent data-driven approaches utilize multiple interpolations through intermediate database shapes, and consequently perform better at the expense of a database requirement. In contrast to the existing data-driven approaches that consider intermediate shape...
Shape models based on elliptic PDES, associated energies, and their applications in 2D and 3D Gençtav, Aslı; Tarı, Zehra Sibel; Can, Tolga; Department of Computer Engineering (2018) By using an elliptic PDE or its modifications, we develop implicit shape representations and demonstrate their two- and three-dimensional applications. In the first part of the thesis, we present a novel shape characterization field that provides a local measure of roundness at each shape point. The field is computed by comparing the solution of the elliptic PDE on the shape domain and the solution of the same PDE on the reference disk. We demonstrate its potential via illustrative applications including gl...
3D Correspondence by Breadth First Search Frontiers Sahillioğlu, Yusuf (null; 2009-06-01) This paper presents a novel, robust, and fast 3D shape correspondence algorithm applicable to the two snapshots of the same object in arbitrary deformation. Given two such frames as triangle meshes with fixed connectivity, our algorithm first classifies vertices into Breadth-First Search (BFS) frontiers according to their unweighted shortest path distance from a source vertex. This is followed by the rigid or non-rigid alignment of the corresponding frontiers of two meshes as the second and final step. This...
Detail-Preserving Mesh Unfolding for Nonrigid Shape Retrieval Sahillioğlu, Yusuf (2016-06-01) We present a shape deformation algorithm that unfolds any given 3D shape into a canonical pose that is invariant to nonrigid transformations. Unlike classical approaches, such as least-squares multidimensional scaling, we preserve the geometric details of the input shape in the resulting shape, which in turn leads to a content-based nonrigid shape retrieval application with higher accuracy. Our optimization framework, fed with a triangular or a tetrahedral mesh in 3D, tries to move each vertex as far away f...
Coarse-to-fine surface reconstruction from silhouettes and range data using mesh deformation Sahillioğlu, Yusuf; Yemez, Y. (2010-03-01) We present a coarse-to-fine surface reconstruction method based on mesh deformation to build watertight surface models of complex objects from their silhouettes and range data. The deformable mesh, which initially represents the object visual hull, is iteratively displaced towards the triangulated range surface using the line-of-sight information. Each iteration of the deformation algorithm involves smoothing and restructuring operations to regularize the surface evolution process. We define a non-shrinking...

Citation Formats

M. Aydinlilar and Y. Sahillioğlu, “Part-based data-driven 3D shape interpolation,” COMPUTER-AIDED DESIGN, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/90690.