Deep Learning Advances in Computer Vision with 3D Data

Ioannidou, Anastasia; Chatzilari, Elisavet; Nikolopoulos, Spiros; Kompatsiaris, Ioannis

doi:10.1145/3042064

Cited by 295 publications

(155 citation statements)

References 142 publications

Supporting

Mentioning

153

Contrasting

Unclassified

Order By: Relevance

“…Neural networks [43] are a common machine learning algorithm that have been particularly successful in two-dimensional image recognition tasks [43][44][45]. This success has led researchers to apply similar methodology to 3D recognition tasks [46], facilitated by recent advances in computing that enable such tasks to be performed at scale. Seminal 3D classification datasets and efforts include ObjectNet3D [47], ShapeNet [48], VoxNet [49], and PointNet [50].…”

Section: Machine Learning To Predict Am Qualitymentioning

confidence: 99%

Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns

McComb¹,

Meisel²,

Simpson³

et al. 2018

Preprint

View full text Add to dashboard Cite

Additive Manufacturing (AM) allows designers to create intricate geometries that were once too complex or expensive to achieve through traditional manufacturing processes. Currently, Design for Additive Manufacturing (DfAM) is restricted to experts in the field, and novices may overlook potentially transformational design potential enabled by AM. This project aims to make DfAM accessible to a broader audience through deep learning, enabling designers of all skill levels to leverage unique AM geometries when creating new designs. To demonstrate such an approach, a database of files was acquired from industry-sponsored AM challenges focused on lightweight design. These files were converted to a voxelized format, which provides more robust information for machine learning applications. Next, an autoencoder was constructed to a low-dimensional representation of the part designs. Finally, that autoencoder was used to construct a deep neural network capable of predicting various DfAM attributes. This work demonstrates a novel foray towards a more extensive DfAM support system that supports designers at all experience levels.

show abstract

Section: Machine Learning To Predict Am Qualitymentioning

confidence: 99%

Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns

McComb¹,

Meisel²,

Simpson³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…The input and outputs of the method; a) raw point cloud of the cluttered indoor environment; b) direct application of previously trained CNN classifier to the test site; c) selection of the wall points determined by the CNN; d) the result of the planar extraction, applied only to the corresponding wall points any object detection or pre-segmentation. A detailed survey can be found in the survey of Ioannidou et al, (2017).…”

Section: Convolutional Neural Network On 3d Datamentioning

confidence: 99%

Semantic Segmentation of Indoor Point Clouds Using Convolutional Neural Network

Babacan

Chen

Sohn

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:As Building Information Modelling (BIM) thrives, geometry becomes no longer sufficient; an ever increasing variety of semantic information is needed to express an indoor model adequately. On the other hand, for the existing buildings, automatically generating semantically enriched BIM from point cloud data is in its infancy. The previous research to enhance the semantic content rely on frameworks in which some specific rules and/or features that are hand coded by specialists. These methods immanently lack generalization and easily break in different circumstances. On this account, a generalized framework is urgently needed to automatically and accurately generate semantic information. Therefore we propose to employ deep learning techniques for the semantic segmentation of point clouds into meaningful parts. More specifically, we build a volumetric data representation in order to efficiently generate the high number of training samples needed to initiate a convolutional neural network architecture. The feedforward propagation is used in such a way to perform the classification in voxel level for achieving semantic segmentation. The method is tested both for a mobile laser scanner point cloud, and a larger scale synthetically generated data. We also demonstrate a case study, in which our method can be effectively used to leverage the extraction of planar surfaces in challenging cluttered indoor environments.

show abstract

“…The most relevant is a recent survey covering the advances of 3D computer vision due to deep learning, and the details of the techniques and network architectures used to make these advances. 14 We seek to provide a higher-level view of the field with a purpose of providing broader understanding and inspiration for future work in computer vision and related fields. We give brief overviews of topics like training deep neural networks, which we trust the reader can find abundant resources on, and we focus more on what the neural networks can do as well as specific details relevant to 3D computer vision.…”

Section: Related Workmentioning

confidence: 99%

“…There are relatively few published works summarizing the state of affairs for 3D computer vision. The most relevant is a recent survey covering the advances of 3D computer vision due to deep learning, and the details of the techniques and network architectures used to make these advances . We seek to provide a higher‐level view of the field with a purpose of providing broader understanding and inspiration for future work in computer vision and related fields.…”

Section: Introductionmentioning

confidence: 99%

3D computer vision based on machine learning with deep neural networks: A review

Bhowmik

2017

J Soc Info Display

View full text Add to dashboard Cite

Recent advances in the field of computer vision can be attributed to the emergence of deep learning techniques, in particular convolutional neural networks. Neural networks, partially inspired by the brain's visual cortex, enable a computer to “learn” the most important features of the images it is shown in relation to a specific, specified task. Given sufficient data and time, (deep) convolutional neural networks offer more easily designed, more generalizable, and significantly more accurate end‐to‐end systems than is possible with previously employed computer vision techniques. This review paper seeks to provide an overview of deep learning in the field of computer vision with an emphasis on recent progress in tasks involving 3D visual data. Through a backdrop of the mammalian visual processing system, we hope to also provide inspiration for future advances in automated visual processing.

show abstract

Deep Learning Advances in Computer Vision with 3D Data

Cited by 295 publications

References 142 publications

Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns

Predicting Part Mass, Required Support Material, and Build Time via Autoencoded Voxel Patterns

Semantic Segmentation of Indoor Point Clouds Using Convolutional Neural Network

3D computer vision based on machine learning with deep neural networks: A review

Contact Info

Product

Resources

About