Genetic algorithms for 3d reconstruction with supershapes

Voisin, Sophie; Abidi, Mongi A.; Foufou, Sebti; Truchetet, Frédéric

doi:10.1109/icip.2009.5413905

Cited by 12 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To alleviate this, Vaskevicius and Birk [29] introduced a numerically stable method of computing the gradient of the inside-outside function with respect to the superquadric parameters, making possible to better model shapes, such as cuboids and cylinders. Others have approached the recovery procedure from another perspective, for example, by using genetic algorithms [11]. Extensions to superquadrics were also proposed [30], [31], but ultimately these also relied on iterative optimization procedures during recovery, which stalled further development in this direction.…”

Section: A Superquadric Recoverymentioning

confidence: 99%

Learning to Predict Superquadric Parameters From Depth Images With Explicit and Implicit Supervision

et al. 2021

View full text Add to dashboard Cite

Reconstruction of 3D space from visual data has always been a significant challenge in the field of computer vision. A popular approach to address this problem can be found in the form of bottom-up reconstruction techniques which try to model complex 3D scenes through a constellation of volumetric primitives. Such techniques are inspired by the current understanding of the human visual system and are, therefore, strongly related to the way humans process visual information, as suggested by recent visual neuroscience literature. While advances have been made in recent years in the area of 3D reconstruction, the problem remains challenging due to the many possible ways of representing 3D data, the ambiguity of determining the shape and general position in 3D space and the difficulty to train efficient models for the prediction of volumetric primitives. In this paper, we address these challenges and present a novel solution for recovering volumetric primitives from depth images. Specifically, we focus on the recovery of superquadrics, a special type of parametric models able to describe a wide array of 3D shapes using only a few parameters. We present a new learning objective that relies on the superquadric (inside-outside) function and develop two learning strategies for training convolutional neural networks (CNN) capable of predicting superquadric parameters. The first uses explicit supervision and penalizes the difference between the predicted and reference superquadric parameters. The second strategy uses implicit supervision and penalizes differences between the input depth images and depth images rendered from the predicted parameters. CNN predictors for superquadric parameters are trained with both strategies and evaluated on a large dataset of synthetic and real-world depth images. Experimental results show that both strategies compare favourably to the existing state-of-the-art and result in high quality 3D reconstructions of the modelled scenes at a much shorter processing time.

show abstract

Section: A Superquadric Recoverymentioning

confidence: 99%

Learning to Predict Superquadric Parameters From Depth Images With Explicit and Implicit Supervision

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Other researchers have tried to improve this method in various ways, for example in modifying the fitting function [12], or using multiresolution [13] but still essentially relying on iterative methods of minimizing the fitting function. Instead of gradient least-squares minimization, other methods of minimization have also been tried, such as genetic algorithms [14]. Several extensions of superquadrics were proposed in the literature [15], [16], however, the basic superquadric shape model and the recovery method of Solina and Bajcsy prevailed in most applications of superquadrics, in particular for path and grasp planning in robotics, for modelling and interpretation of medical images etc.…”

Section: Related Workmentioning

confidence: 99%

Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study

Oblak,

Grm,

Jaklič

et al. 2019

Preprint

View full text Add to dashboard Cite

It has been a longstanding goal in computer vision to describe the 3D physical space in terms of parameterized volumetric models that would allow autonomous machines to understand and interact with their surroundings. Such models are typically motivated by human visual perception and aim to represents all elements of the physical word ranging from individual objects to complex scenes using a small set of parameters. One of the de facto stadards to approach this problem are superquadrics -volumetric models that define various 3D shape primitives and can be fitted to actual 3D data (either in the form of point clouds or range images). However, existing solutions to superquadric recovery involve costly iterative fitting procedures, which limit the applicability of such techniques in practice. To alleviate this problem, we explore in this paper the possibility to recover superquadrics from range images without time consuming iterative parameter estimation techniques by using contemporary deep-learning models, more specifically, convolutional neural networks (CNNs). We pose the superquadric recovery problem as a regression task and develop a CNN regressor that is able to estimate the parameters of a superquadric model from a given range image. We train the regressor on a large set of synthetic range images, each containing a single (unrotated) superquadric shape and evaluate the learned model in comparaitve experiments with the current state-of-theart. Additionally, we also present a qualitative analysis involving a dataset of real-world objects. The results of our experiments show that the proposed regressor not only outperforms the existing state-of-the-art, but also ensures a 270× faster execution time.

show abstract

“…Bokhabrine et al [8] used a GA to evolve all supershape parameters for surface reconstruction (i.e., a target-based approach) using an inside-outside function [20] for fitness. Voisin et al [79] later extended this to utilise a pseudo-Euclidean distance for fitness determination, yielding improved performance.…”

Section: Gielis Superformulamentioning

confidence: 99%

Towards the evolution of vertical-axis wind turbines using supershapes

Preen

Bull

2014

Evol. Intel.

View full text Add to dashboard Cite

We have recently presented an initial study of evolutionary algorithms used to design vertical-axis wind turbines (VAWTs) wherein candidate prototypes are evaluated under fan generated wind conditions after being physically instantiated by a 3D printer. That is, unlike other approaches such as computational fluid dynamics simulations, no mathematical formulations are used and no model assumptions are made. However, the representation used significantly restricted the range of morphologies explored. In this paper, we present initial explorations into the use of a simple generative encoding, known as Gielis superformula, that produces a highly flexible 3D shape representation to design VAWT. First, the target-based evolution of 3D artefacts is investigated and subsequently initial design experiments are performed wherein each VAWT candidate is physically instantiated and evaluated under fan generated wind conditions. It is shown possible to produce very closely matching designs of a number of 3D objects through the evolution of supershapes produced by Gielis superformula. Moreover, it is shown possible to use artificial physical evolution to identify novel and increasingly efficient supershape VAWT designs.

show abstract

Genetic algorithms for 3d reconstruction with supershapes

Cited by 12 publications

References 21 publications

Learning to Predict Superquadric Parameters From Depth Images With Explicit and Implicit Supervision

Learning to Predict Superquadric Parameters From Depth Images With Explicit and Implicit Supervision

Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study

Towards the evolution of vertical-axis wind turbines using supershapes

Contact Info

Product

Resources

About