Single-view reconstruction via joint analysis of image and shape collections

Huang, Qixing; Wang, Hai; Koltun, Vladlen

doi:10.1145/2766890

Cited by 135 publications

(91 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Very recent work has considered the problem of surface reconstruction from single RGB images [SHM*14, HWK15]. These techniques are data‐driven, in that they rely on large‐shape collections to estimate either depth or a full 3D model strictly from a single image.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Surface Reconstruction from Point Clouds

Berger

Tagliasacchi

Seversky

et al. 2016

Computer Graphics Forum

465

354

View full text Add to dashboard Cite

The area of surface reconstruction has seen substantial progress in the past two decades. The traditional problem addressed by surface reconstruction is to recover the digital representation of a physical shape that has been scanned, where the scanned data contain a wide variety of defects. While much of the earlier work has been focused on reconstructing a piece‐wise smooth representation of the original shape, recent work has taken on more specialized priors to address significantly challenging data imperfections, where the reconstruction can take on different representations—not necessarily the explicit geometry. We survey the field of surface reconstruction, and provide a categorization with respect to priors, data imperfections and reconstruction output. By considering a holistic view of surface reconstruction, we show a detailed characterization of the field, highlight similarities between diverse reconstruction techniques and provide directions for future work in surface reconstruction.

show abstract

Section: Introductionmentioning

confidence: 99%

A Survey of Surface Reconstruction from Point Clouds

Berger

Tagliasacchi

Seversky

et al. 2016

Computer Graphics Forum

465

354

View full text Add to dashboard Cite

show abstract

“…By employing this information, the 3D reconstruction becomes much easier. In (Su et al 2014) and (Huang, Wang, and Koltun 2015), the authors reconstructed the depth of objects from web-site collected images by exploiting a collection of aligned 3D models of related objects shape. In (Karimi Mahabadi, Hane, and Pollefeys 2015), a novel shape prior formulation is proposed to split the object into multiple convex parts and then the reconstruction is formulated as a volumetric multi-label segmentation problem.…”

Section: Shape Prior Guided 3d Reconstructionmentioning

confidence: 99%

RealPoint3D: Generating 3D Point Clouds from a Single Image of Complex Scenarios

Xia

Wang

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

3D point cloud generation by the deep neural network from a single image has been attracting more and more researchers' attention. However, recently-proposed methods (e.g., (Fan, Su, and Guibas 2017)) require the objects be captured with relatively clean backgrounds, fixed viewpoint, while this highly limits its application in the real environment. To overcome these drawbacks, we proposed to integrate the prior 3D shape knowledge into the network to guide the 3D generation. By taking additional 3D information, the proposed network can handle the 3D object generation from a single real image captured from any viewpoint and complex background. Specifically, giving a query image, we retrieve the nearest shape model from a pre-prepared 3D model database. Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud. The effectiveness of our proposed framework has been verified on different kinds of datasets. Experimental results show that the proposed framework achieves state-of-the-art accuracy compared to other volumetric-based and point set generation methods. Furthermore, the proposed framework works well for real images in complex backgrounds with various view angles.

show abstract

“…Huang et al . [HWK15] jointly analyse a large collection of images in object categories and a smaller collection of 3D models to achieve simultaneous analysis and reconstruction of 2D images.…”

Section: Shape Reconstructionmentioning

confidence: 99%

“…In a recent work, Su et al [SHM*14] propose to learn meaningful deformations of each shape from its optimal deformation to similar shapes. Huang et al [HWK15] jointly analyse a large collection of images in object categories and a smaller collection of 3D models to achieve simultaneous analysis and reconstruction of 2D images.…”

Section: Example-based Scan Completion Pauly Et Almentioning

confidence: 99%

Data‐Driven Shape Analysis and Processing

Kim

Huang

et al. 2016

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

Data‐driven methods serve an increasingly important role in discovering geometric, structural and semantic relationships between shapes. In contrast to traditional approaches that process shapes in isolation of each other, data‐driven methods aggregate information from 3D model collections to improve the analysis, modelling and editing of shapes. Data‐driven methods are also able to learn computational models that reason about properties and relationships of shapes without relying on hard‐coded rules or explicitly programmed instructions. Through reviewing the literature, we provide an overview of the main concepts and components of these methods, as well as discuss their application to classification, segmentation, matching, reconstruction, modelling and exploration, as well as scene analysis and synthesis. We conclude our report with ideas that can inspire future research in data‐driven shape analysis and processing.

show abstract

Single-view reconstruction via joint analysis of image and shape collections

Cited by 135 publications

References 35 publications

A Survey of Surface Reconstruction from Point Clouds

A Survey of Surface Reconstruction from Point Clouds

RealPoint3D: Generating 3D Point Clouds from a Single Image of Complex Scenarios

Data‐Driven Shape Analysis and Processing

Contact Info

Product

Resources

About