Estimation of human body shape and cloth field in front of a kinect

Zhang, Ming; Cao, Liujuan; Dong, Hua; Lin, Kwei-Jay; Mei-hong, Wang; Tong, Jing

doi:10.1016/j.neucom.2014.06.087

Cited by 13 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use dressed‐human silhouettes as input, which is more convenient for users. Some works [HSR*09, WPB*14, NH14, ZCD*15] taking 3D scanning points as input required 3D scanners. Zhu et.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…al. [ZCD*15] used the RGB image to detect skin areas as tight constraints for body shapes estimation. These methods should find correspondences between input 3D dense points and target mesh vertices, which is time‐consuming.…”

Section: Related Workmentioning

confidence: 99%

“…Due to projecting dressed shapes to the body space, the estimated body is usually fatter than ground truth. Skin areas show more confidence for shapes so that some researchers set higher weight for the exposed‐skin part of input information [BB08, ZCD*15]. Consequently, this kind of method relies on skin areas and still leaves the covered body shapes ambiguous.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3D Body Shapes Estimation from Dressed‐Human Silhouettes

Song

Tong

Chang

et al. 2016

Computer Graphics Forum

View full text Add to dashboard Cite

Estimation of 3D body shapes from dressed-human photos is an important but challenging problem in virtual fitting. We propose a novel automatic framework to efficiently estimate 3D body shapes under clothes. We construct a large database of 3D naked and dressed body pairs, based on which we learn how to predict 3D positions of body landmarks (which further constrain a parametric human body model) automatically according to dressed-human silhouettes. Critical vertices are selected on 3D registered human bodies as landmarks to represent body shapes, so as to avoid the time-consuming vertices correspondences finding process for parametric body reconstruction. Our method can estimate 3D body shapes from dressed-human silhouettes within 4 seconds, while the fastest method reported previously need 1 minute. In addition, our estimation error is within the size tolerance for clothing industry. We dress 3D naked bodies with one set of common clothes acquired by physically based cloth simulation technique. To the best of our knowledge, We are the first to construct a large database containing 3D naked and dressed body pairs and our database may contribute to the areas of human body shapes estimation and cloth simulation.

show abstract

“…We use dressed‐human silhouettes as input, which is more convenient for users. Some works [HSR*09, WPB*14, NH14, ZCD*15] taking 3D scanning points as input required 3D scanners. Zhu et.…”

Section: Experiments Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D Body Shapes Estimation from Dressed‐Human Silhouettes

Song

Tong

Chang

et al. 2016

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Most often, raw 59 data comes from acquisition of people wearing clothes and this 60 may lead to non-realistic bodies. Bȃlan and Black (2008), as 61 well as Zeng et al (2015) intend to find ways to pass through 62 these limitations. Since they rely only on skin models and 63 do not include internal anatomy, those methods may result in 64 unrealistic skin twisting.…”

Section: Related Workmentioning

confidence: 99%

Anatomical augmented reality with 3D commodity tracking and image-space alignment

Bauer

Neog

Dicko

et al. 2017

Computers & Graphics

View full text Add to dashboard Cite

International audienceThis paper presents a mirror-like augmented reality (AR) system to display the internal anatomy of the current user. Using a single Microsoft V2.0 Kinect (later on referenced as the Kinect), we animate in real-time a user-specific model of internal anatomy according to the user’s motion and we superimpose it onto the user’s color map. Userscan visualize their anatomy moving as if they where looking inside their own bodies in real-time.A new calibration procedure to set up and attach a user-specific anatomy to the Kinect body tracking skeleton is introduced. At calibration time, the bone lengths are estimated using a set of poses. By using Kinect data as input, the practical limitation of skin correspondence in prior work is overcome. The generic 3D anatomical model is attached to the internal anatomy registration skeleton, and warped on the depth image using a novel elastic deformer subject to a closest-point registration force and anatomical constraints. The noise in Kinect outputs precludes direct display of realistic human anatomy. Therefore, to enforce anatomical plausibility, a novel filter to reconstruct plausiblemotions based on fixed bones lengths as well as realistic angular degrees of freedom DOFs) and limits are introduced. Anatomical constraints, applied to the Kinect body tracking skeleton joints, are used to maximize the physical plausibility of the anatomy motion while minimizing the distance to the raw data. At run-time, a simulation loop is used to attract the bones towards the raw data. Skinning shaders efficiently drag the resulting anatomy to the user’s tracked motion. Our user-specific internal anatomy model is validated by comparing the skeleton withsegmented MRI images. A user study is established to evaluate the believability of the animated anatomy.As an extension of Bauer et al. (2016), we also propose an image-based algorithm that corrects accumulated inaccuracy of the system steps: motion capture, anatomy transfer, image generation and animation. These inaccuracies show up as occlusion and self-occlusion misalignments of the anatomy regions when superimposed between them and on top of the color map. We also show that the proposed work can efficiently reduce these inaccuracies

show abstract

“…Most often, raw data come from acquisition of people wearing clothes and this may lead to non-realistic bodies (part proportions, etc). [Bȃlan and Black 2008] and [Zeng et al 2015] intend to find ways to pass through these limitations. Since they rely only on skin models and do not include internal anatomy, those methods may result in unrealistic skin twisting.…”

Section: Related Workmentioning

confidence: 99%