3D-Mask-GAN:Unsupervised Single-View 3D Object Reconstruction

Wan, Qun; Li, Yidong; Cui, Haidong; Feng, Zheng

doi:10.1109/besc48373.2019.8963264

Cited by 8 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some examples in the literature show that it is possible to use semantic image segmentation to eliminate the effect of moving objects in images (Nooruddin et al, 2018) or using the relative camera orientation to find a reliable object segmentation to increase the accurate 3D reconstruction (Mohammed et al, 2019). However, these and similar works (Kaneko et al, 2018;Wan et al, 2019) address the problem of continuous artifacts, while the domain issue is related to discontinuous elements structured according to spatial grids. The recent advances in Deep Learning methods represent a cutting-edge approach to solving very long and repetitive process, producing high-quality outputs.…”

Section: Related Workmentioning

confidence: 99%

Geometric Analysis of a Space Grid Structure by an Integrated 3d Survey Approach

Russo

Russo²

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The survey and modeling of spatial grid structures is often a challenging task to solve, due to the many bottlenecks present in the reverse modelling process. Geometrical and material complexity, scale variation, shadows effects, low accessibility, mismatch between similar elements, metrical validation, data management are all critical passages. They must be solved to obtain a reliable data able to solve the system maintenance and intervention requirements. In these cases, in particular, when the structure is difficult to be accessed, it is essential to plan an integrated survey approach. This paper shows how the survey and modelling of an impressive structure was carried out using both TLS and RPAS photogrammetry. After being validated, the data is integrated into a single point cloud that completely describes the structure, eliminating shadow areas and hidden parts. In the modeling process, particular attention was paid to verifying the correspondence between as-built and project. Finally, an element of particular interest is represented by the attempt to recognize the individual construction components belonging to specified geometric and dimensional classes, with the advantage of obtaining a complete model that is as faithful as possible to the real situation of the structure.

show abstract

Section: Related Workmentioning

confidence: 99%

Geometric Analysis of a Space Grid Structure by an Integrated 3d Survey Approach

Russo

Russo²

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…It is worth noting that GANs can be employed to efficiently generate and reconstruct videos, reconstruct 3D objects from 2D data and even generate complete 3D models. In [31], the authors presented an efficient framework able to generate 3D object shapes. In this work, a 3D-Mask-GAN was used to predict 3D structures from a single-view image.…”

Section: Gan Basedmentioning

confidence: 99%

Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case

et al. 2021

View full text Add to dashboard Cite

Data-driven methods—particularly machine learning techniques—are expected to play a key role in the headway of Industry 4.0. One increasingly popular application in this context is when anomaly detection is employed to test manufactured goods in assembly lines. In this work, we compare supervised, semi/weakly-supervised, and unsupervised strategies to detect anomalous sequences in video samples which may be indicative of defective televisions assembled in a factory. We compare 3D autoencoders, convolutional neural networks, and generative adversarial networks (GANs) with data collected in a laboratory. Our methodology to simulate anomalies commonly found in TV devices is discussed in this paper. We also propose an approach to generate anomalous sequences similar to those produced by a defective device as part of our GAN approach. Our results show that autoencoders perform poorly when trained with only non-anomalous data—which is important because class imbalance in industrial applications is typically skewed towards the non-anomalous class. However, we show that fine-tuning the GAN is a feasible approach to overcome this problem, achieving results comparable to those of supervised methods.

show abstract

“…A method [37] utilises the camera relative orientation of a pair of images to find a reliable object segmentation for further accurate 3D reconstruction. But these and some more related works [38][39][40] addresses to the problem of continuous (not grid-structured) objects. Recent impressive progress in deep learning methods makes them powerful mean for solving various complicated task with high quality.…”

Section: Grid Structures 3d Reconstructionmentioning

confidence: 99%

3D Reconstruction of a Complex Grid Structure Combining UAS Images and Deep Learning

et al. 2020

View full text Add to dashboard Cite

The latest advances in technical characteristics of unmanned aerial systems (UAS) and their onboard sensors opened the way for smart flying vehicles exploiting new application areas and allowing to perform missions seemed to be impossible before. One of these complicated tasks is the 3D reconstruction and monitoring of large-size, complex, grid-like structures as radio or television towers. Although image-based 3D survey contains a lot of visual and geometrical information useful for making preliminary conclusions on construction health, standard photogrammetric processing fails to perform dense and robust 3D reconstruction of complex large-size mesh structures. The main problem of such objects is repeated and self-occlusive similar elements resulting in false feature matching. This paper presents a method developed for an accurate Multi-View Stereo (MVS) dense 3D reconstruction of the Shukhov Radio Tower in Moscow (Russia) based on UAS photogrammetric survey. A key element for the successful image-based 3D reconstruction is the developed WireNetV2 neural network model for robust automatic semantic segmentation of wire structures. The proposed neural network provides high matching quality due to an accurate masking of the tower elements. The main contributions of the paper are: (1) a deep learning WireNetV2 convolutional neural network model that outperforms the state-of-the-art results of semantic segmentation on a dataset containing images of grid structures of complicated topology with repeated elements, holes, self-occlusions, thus providing robust grid structure masking and, as a result, accurate 3D reconstruction, (2) an advanced image-based pipeline aided by a neural network for the accurate 3D reconstruction of the large-size and complex grid structured, evaluated on UAS imagery of Shukhov radio tower in Moscow.

show abstract

3D-Mask-GAN:Unsupervised Single-View 3D Object Reconstruction

Cited by 8 publications

References 10 publications

Geometric Analysis of a Space Grid Structure by an Integrated 3d Survey Approach

Geometric Analysis of a Space Grid Structure by an Integrated 3d Survey Approach

Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case

3D Reconstruction of a Complex Grid Structure Combining UAS Images and Deep Learning

Contact Info

Product

Resources

About