Part-based data-driven shape interpolation

Download
2018
Aydınlılar, Melike
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 rigid parts. In particular, we interpolate rigid 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 demonstrate visually appealing and natural shape interpolation results in comparison with two other techniques. As a side contribution, we provide a public articulated hand dataset with fixed connectivity, which can be used in the evaluation of other shape interpolation methods. Our code and executables are also publicly available.

Suggestions

Part-based data-driven 3D shape interpolation
Aydinlilar, Melike; Sahillioğlu, Yusuf (2021-07-01)
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...
Part-Aware Distance Fields for Easy Inbetweening in Arbitrary Dimensions
Tarı, Zehra Sibel (2013-07-01)
The motivation for this work is to explore a possible computer graphics application for a part aware distance field developed recently. Computing in-between shapes is chosen as a toy application. Rather than presenting a highly competitive scheme which continuously morphs one shape into another, our aim is to investigate whether in-betweens may be defined as ordinary averages once a proper shape representation (e.g. a part aware field) is established. The constructions are independent of the dimension of th...
Object recognition and segmentation via shape models
Altınoklu, Metin Burak; Ulusoy, İlkay; Tarı, Zehra Sibel; Department of Electrical and Electronics Engineering (2016)
In this thesis, the problem of object detection, recognition and segmentation in computer vision is addressed with shape based methods. An efficient object detection method based on a sparse skeleton has been proposed. The proposed method is an improved chamfer template matching method for recognition of articulated objects. Using a probabilistic graphical model structure, shape variation is represented in a skeletal shape model, where nodes correspond to parts consisting of lines and edges correspond to pa...
A comparative study on pose estimation algorithms using visual data
Çetinkaya, Güven; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2012)
Computation of the position and orientation of an object with respect to a camera from its images is called pose estimation problem. Pose estimation is one of the major problems in computer vision, robotics and photogrammetry. Object tracking, object recognition, self-localization of robots are typical examples for the use of pose estimation. Determining the pose of an object from its projections requires 3D model of an object in its own reference system, the camera parameters and 2D image of the object. Mo...
Head modeling with camera auto-calibration and deformation
Hassanpour, R; Atalay, Mehmet Volkan (2002-01-01)
A 3D head modeling method from a sequence of 2D images is described. The views from which the input images are acquired are not calibrated., Therefore, an auto-calibration method for a sequence of images with small rotations and translation is developed. For this purpose, we have modified an already existing auto-calibration algorithm to incorporate known aspect ratio and skew values to make it applicable for small rotation around a single axis. We apply this auto-calibration technique to head (face) modeli...
Citation Formats
M. Aydınlılar, “Part-based data-driven shape interpolation,” M.S. - Master of Science, Middle East Technical University, 2018.