Multilevel active registration for kinect human body scans: from low quality to high quality

Xu, Zongyi; Zhang, Qianni; Cheng, Shiyang

doi:10.1007/s00530-017-0541-1

Cited by 15 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiments, we use a wide selection of data collected from nine datasets exhibiting a variety of resolutions, sampling, surface artefacts and partiality. Specifically, we used: FAUST [BRLB14], Princeton Segmentation Benchmark [CGF09], TOSCA [BBK08], CAESAR [RDP99], KIDS [RRBW*14], SHREC'11 [BBB*11], SHREC'14 [PSR*16], SPRING [YYZ*14] and K3D‐hub [XZC17]. All shapes were rescaled and downsampled to a similar density as the parametric model via edge collapse [GH97], and small artefacts were fixed using MeshFix [AF06].…”

Section: Registration Resultsmentioning

confidence: 99%

FARM: Functional Automatic Registration Method for 3D Human Bodies

Marin

Melzi

Rodolà

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

We introduce a new method for non‐rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of the human, and makes use of the functional map representation for encoding and inferring shape maps throughout the registration process. This combination endows our method with robustness to a large variety of nuisances observed in practical settings, including non‐isometric transformations, downsampling, topological noise and occlusions; further, the pipeline can be applied invariably across different shape representations (e.g. meshes and point clouds), and in the presence of (even dramatic) missing parts such as those arising in real‐world depth sensing applications. We showcase our method on a selection of challenging tasks, demonstrating results in line with, or even surpassing, state‐of‐the‐art methods in the respective areas.

show abstract

Section: Registration Resultsmentioning

confidence: 99%

FARM: Functional Automatic Registration Method for 3D Human Bodies

Marin

Melzi

Rodolà

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…There are multiple datasets of static 3D body scans available to the research community. Some are freely available for research [7,42,20,27,9,40,11], others are commercial such as [30]. They are reviewed and discussed below with their advantages and disadvantages.…”

Section: Related Datasetsmentioning

confidence: 99%

“…The Kinect-based 3D human body (K3D-hub) dataset [40] is made of 250 low-quality human body scans acquired with the Microsoft Kinect sensor. It contains 50 different subjects in 5 different poses.…”

Section: Related Datasetsmentioning

confidence: 99%

“…The pipeline presented in this section improves upon related works striving towards automation. It does not make any assumption on the input pose [21,40,28], e.g. the "A" pose.…”

Section: Proposed Automatic Fitting To a 3d Scanmentioning

confidence: 99%

“…Modelling the 3D body shape has applications in fashion, ergonomics, online retail, entertainment and other industries. As 3D scanners have become mainstream, several datasets of 3D body scans have been collected and proposed for research or commercial purposes [7,42,20,27,9,40,11,30]. The content of the datasets varies depending on the aim and the method of acquisition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3DBodyTex: Textured 3D Body Dataset

Saint

Ahmed

Shabayek

et al. 2018

2018 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

In this paper, a dataset, named 3DBodyTex, of static 3D body scans with high-quality texture information is presented along with a fully automatic method for body model fitting to a 3D scan. 3D shape modelling is a fundamental area of computer vision that has a wide range of applications in the industry. It is becoming even more important as 3D sensing technologies are entering consumer devices such as smartphones. As the main output of these sensors is the 3D shape, many methods rely on this information alone. The 3D shape information is, however, very high dimensional and leads to models that must handle many degrees of freedom from limited information. Coupling texture and 3D shape alleviates this burden, as the texture of 3D objects is complementary to their shape. Unfortunately, high-quality texture content is lacking from commonly available datasets, and in particular in datasets of 3D body scans. The proposed 3DBodyTex dataset aims to fill this gap with hundreds of high-quality 3D body scans with high-resolution texture. Moreover, a novel fully automatic pipeline to fit a body model to a 3D scan is proposed. It includes a robust 3D landmark estimator that takes advantage of the high-resolution texture of 3DBodyTex. The pipeline is applied to the scans, and the results are reported and discussed, showcasing the diversity of the features in the dataset.

show abstract