Generative Adversarial Networks as an Advancement in 2D to 3D Reconstruction Techniques

Dhondse, Amol; Kulkarni, Siddhivinayak; Khadilkar, Kunal; Kane, Indrajeet; Chavan, Sumit; Barhate, Rahul

doi:10.1007/978-981-13-9364-8_25

Cited by 3 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first one is the advancements in machine learning research. The growing use of artificial neural networks (ANNs) in computational design is a reflection of the fast advancement in research in generative models (Dhondse, 2020) and true distributions (Alcin, 2019). This is as well as the increasing computational power available and training data sets available (Hodas & Stinis, 2018).…”

Section: Self-organizing Floor Plan At Workmentioning

confidence: 99%

Self-Organizing Floor Plans

Carta

2021

Harvard Data Science Review

View full text Add to dashboard Cite

This article introduces and comments on some of the techniques currently used by designers to generate automatic building floor plans and spatial configurations in general, with emphasis on machine learning and neural networks models. This is a relatively new tendency in computational design that reflects a growing interest in advanced generative and optimization models by architects and building engineers.The first part of this work contextualizes self-organizing floor plans in architecture and computational design, highlighting their importance and potential for designers as well as software developers. The central part discusses some of the most common techniques with concrete examples, including Neuro Evolution of Augmenting Topologies (NEAT) and Generative Adversarial Networks (GAN). The final section of the article provides some general comments considering pitfalls and possible future developments, as well as speculating on the future of this trend.

show abstract

Section: Self-organizing Floor Plan At Workmentioning

confidence: 99%

Self-Organizing Floor Plans

Carta

2021

Harvard Data Science Review

View full text Add to dashboard Cite

show abstract

“…For example, 3D Recurrent Reconstruction Neural Network (3D-R2N2) for multi-view reconstruction on the Sanford Online Products [19] and ShapeNet [20] datasets, has managed to achieve this task with fewer images available with competitive results [21], with the proposed improvement that uses densely connected structure as encoder and utilizing Chamfer Distance as loss function [22]. Additionally, Generative Adversarial Networks (GANs) can be used to generate 3D objects from multiple 2D views [23] or even from a single image [24]. GANs have also been shown to be able to predict former geometry of damaged objects [25].…”

Section: Introductionmentioning

confidence: 99%

3D Object Reconstruction from Imperfect Depth Data Using Extended YOLOv3 Network

Kulikajevas

Maskeliūnas

Damaševičius

et al. 2020

Sensors

View full text Add to dashboard Cite

State-of-the-art intelligent versatile applications provoke the usage of full 3D, depth-based streams, especially in the scenarios of intelligent remote control and communications, where virtual and augmented reality will soon become outdated and are forecasted to be replaced by point cloud streams providing explorable 3D environments of communication and industrial data. One of the most novel approaches employed in modern object reconstruction methods is to use a priori knowledge of the objects that are being reconstructed. Our approach is different as we strive to reconstruct a 3D object within much more difficult scenarios of limited data availability. Data stream is often limited by insufficient depth camera coverage and, as a result, the objects are occluded and data is lost. Our proposed hybrid artificial neural network modifications have improved the reconstruction results by 8.53% which allows us for much more precise filling of occluded object sides and reduction of noise during the process. Furthermore, the addition of object segmentation masks and the individual object instance classification is a leap forward towards a general-purpose scene reconstruction as opposed to a single object reconstruction task due to the ability to mask out overlapping object instances and using only masked object area in the reconstruction process.

show abstract