A sketch-aided retrieval approach for incomplete 3D objects

Lengauer, Stefan; Komar, Alexander; Labrada, Arniel; Karl, Stephan; Trinkl, Elisabeth; Preiner, Reinhold; Bustos, Benjamín; Schreck, Tobias

doi:10.1016/j.cag.2020.02.001

Cited by 8 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our Journal will also be affected by these changes and we are working with many top venues to help in providing both quality control and speedy publication via Special and Technical Sections. This issue features papers from three special sections: 3DOR 2019 [1] , Expressive 2019 [2][3] and Graphics Interface 2019 [4] . Please do browse the Foreword to the Special Sections on Expressive 2019 and Graphics Interface that are closed in this issue.…”

Section: Editorial Notementioning

confidence: 99%

Editorial Note

Jorge¹

2020

Computers & Graphics

View full text Add to dashboard Cite

Section: Editorial Notementioning

confidence: 99%

Editorial Note

Jorge¹

2020

Computers & Graphics

View full text Add to dashboard Cite

“…In this work we present MendNet, a fully automated approach that generates restoration 3D models for 3D shapes, as shown on the right of Figure 1, corresponding to 3D models that have undergone fracture‐based damage by learning the relationship between fractured, restoration, and complete shapes. The restoration of fractured shapes has significant impact in fields such as industrial recycling [ZLC06], cultural heritage [LKL∗20; PSA∗17; SCC∗11; SAF∗18], paleontology [SJW∗14], medical applications such as dentistry, orthopedics and reconstructive surgery [HHN07; RMV∗10; WKCF16], and consumer‐focused repair.…”

Section: Introductionmentioning

confidence: 99%

MendNet: Restoration of Fractured Shapes Using Learned Occupancy Functions

Lamb

Banerjee

2022

Computer Graphics Forum

View full text Add to dashboard Cite

We provide a novel approach to perform fully automated generation of restorations for fractured shapes using learned implicit shape representations in the form of occupancy functions. Our approach lays the groundwork to perform automated object repair via additive manufacturing. Existing approaches for restoration of fractured shapes either require prior knowledge of object structure such as symmetries between the restoration and the fractured object, or predict restorations as voxel outputs that are impractical for repair at current resolutions. By leveraging learned occupancy functions for restoration prediction, our approach overcomes the curse of dimensionality with voxel approaches, while providing plausible restorations. Given a fractured shape, we fit a function to occupancy samples from the shape to infer a latent code. We apply a learned transformation to the fractured shape code to predict a corresponding code for restoration generation. To ensure physical validity and well‐constrained shape estimation, we contribute a loss that models feasible occupancy values for fractured shapes, restorations, and complete shapes obtained by joining fractured and restoration shapes. Our work overcomes deficiencies of shape completion approaches adapted for repair, and enables consumer‐driven object repair and cultural heritage object restoration. We share our code and a synthetic dataset of fractured meshes from 8 ShapeNet classes at: https://github.com/Terascale-All-sensing-Research-Studio/MendNet.

show abstract

Cross-Modal Search and Exploration of Greek Painted Pottery

Trinkl,

Karl,

Lengauer

et al. 2024

The 3 Dimensions of Digitalised Archaeology

View full text Add to dashboard Cite

This paper focuses on digitally-supported research methods for an important group of cultural heritage objects, the Greek pottery, especially with figured decoration. The design, development and application of new digital methods for searching, comparing, and visually exploring these vases need an interdisciplinary approach to effectively analyse the various features of the vases, like shape, decoration, and manufacturing techniques, and relationships between the vases. We motivate the need and opportunities by a multimodal representation of the objects, including 3D shape, material, and painting. We then illustrate a range of innovative methods for these representations, including quantified surface and capacity comparison, material analysis, image flattening from 3D objects, retrieval and comparison of shapes and paintings, and multidimensional data visualization. We also discuss challenges and future work in this area.

show abstract

A sketch-aided retrieval approach for incomplete 3D objects

Cited by 8 publications

References 17 publications

Editorial Note

Editorial Note

MendNet: Restoration of Fractured Shapes Using Learned Occupancy Functions

Cross-Modal Search and Exploration of Greek Painted Pottery

Contact Info

Product

Resources

About