SHREC'13 Track: Large Scale Sketch-Based 3D Shape Retrieval

Li, B.; Lu, Yijuan; Godil, Afzal; Schreck, Tobias; Aono, Masaki; Johan, Henry; Saavedra, José M.; Tashiro, Shoki

doi:10.2312/3dor/3dor13/089-096

Cited by 19 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, ArchAIDE employed a pre-trained version of the ResNet-101 network based upon ImageNet (Itkin et al 2019:9) for their decoration-based tool and a variant of the PointNet network (Qi et al 2017) for their shape-based tool (Itkin et al 2019:8). Benhabiles and Tabia (2019:3) employed AlexNet which was also created against ImageNet, while Roman-Rangel and colleagues (Roman-Rangel et al 2016:12-13) used a subset of the SHREC'13 dataset of 3D models of generic objects (Li et al 2013). Such pre-trained models have proved successful in their original classification and identification tasks and have been subsequently applied in many other image recognition contexts.…”

Section: Training and Tuningmentioning

confidence: 99%

Archaeological Practice and Digital Automation

HUGGETT¹

2022

Digital Heritage and Archaeology in Practice

View full text Add to dashboard Cite

photogrammetry, and to the digital infrastructures providing data search, retrieval, and archiving facilities.With automation, archaeological tasks are delegated to mechanical, or software, or software-driven machines. This diverges from Susskind and Susskind's fourth stage, 'externalization ' (2015:202), in which the practical expertise of professionals is made available online to non-specialists, a feature which is already present in the systematization of archaeology and is arguably a characteristic of the subject more generally. Different kinds of automation can be highlighted which overlap in different ways.

show abstract

Section: Training and Tuningmentioning

confidence: 99%

Archaeological Practice and Digital Automation

HUGGETT¹

2022

Digital Heritage and Archaeology in Practice

View full text Add to dashboard Cite

show abstract

View selection for sketch-based 3D model retrieval using visual part shape description

2016

View full text Add to dashboard Cite

Hand drawings are the imprints of shapes in human's mind. How a human expresses a shape is a consequence of how he or she visualizes it. A query-by-sketch 3D object retrieval application is closely tied to this concept from two aspects. First, describing sketches must involve elements in a figure that matter most to a human. Second, the representative 2D projection of the target 3D objects should be limited to "the canonical views" from a human cognition perspective. We advocate for these two rules by presenting a new approach for sketch-based 3D object retrieval that describes a 2D shape by the visual protruding parts of its silhouette. Furthermore, we present a list of candidate 2D projections that represent the canonical views of a 3D object. The general rule is that humans would visually avoid part occlusion and symmetry. We quantify the extent of part occlusion of the projected silhouettes of 3D objects by skeletal length computations. Sorting the projected views in the decreasing order of skeletal lengths gives access to a subset of best representative views. We experimentally show how views that cause misinterpretation and mismatching can be detected according to the part occlusion criteria. We also propose criteria for locating side, off axis, or asymmetric views.

show abstract