3D human body reconstruction based on SMPL model

Chen, Dongyue; Song, Yuanyuan; Liang, Fangzheng; Ma, T.; Zhang, Xiaoming; Jia, Tong

doi:10.1007/s00371-022-02453-x

Cited by 9 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As demonstrated in Figure 3 (right), to focus the loss computation on facial details instead of hair and background, we apply masks to images before calculating the losses. We use a DeepLab segmentation network [CZP*18] trained on CelebAMask‐HQ photos [OSF*20; LLWL20]. Empirically we determine it is best to apply a weight of 1.0 on the face, 0.1 on the hair and 0.0 elsewhere.…”

Section: Transforming Faces Across Timementioning

confidence: 99%

What's in a Decade? Transforming Faces Through Time

Chen

Sun²,

Khandelwal

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

How can one visually characterize photographs of people over time? In this work, we describe the Faces Through Time dataset, which contains over a thousand portrait images per decade from the 1880s to the present day. Using our new dataset, we devise a framework for resynthesizing portrait images across time, imagining how a portrait taken during a particular decade might have looked like had it been taken in other decades. Our framework optimizes a family of per‐decade generators that reveal subtle changes that differentiate decades—such as different hairstyles or makeup—while maintaining the identity of the input portrait. Experiments show that our method can more effectively resynthesizing portraits across time compared to state‐of‐the‐art image‐to‐image translation methods, as well as attribute‐based and language‐guided portrait editing models. Our code and data will be available at facesthroughtime.github.io.

show abstract

Section: Transforming Faces Across Timementioning

confidence: 99%

What's in a Decade? Transforming Faces Through Time

Chen

Sun²,

Khandelwal

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…The human body point cloud model generated by it is fixed at 4690 points and relatively orderly. Besides, the SMPL model is used to reconstruct the 3D human body, [52][53][54] which make it is possible to obtain 3D human models of patients simply and quickly through several photos before acupuncture points positioning. The centroid location algorithm 55 is a classic range-free location algorithm.…”

Section: Smpl and The Centroid Location Algorithmmentioning

confidence: 99%

Location of acupuncture points based on graph convolution and 3D deep learning in virtual humans

Zhou

2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Automatic acupoint searching is an indispensable part of intelligent acupuncture robot. Clinical practice have proofed that Dazhu, Fengmen and Xinshu, which could be located by Dazhui, are curative when these points are acupuncture. The existing methods are mainly based on regular or image. The regular‐based methods are based on the experience of physicians, and the accuracy will decrease for different patients; While the image‐based methods will lose some features in image. In order to solve the existing problems, we propose a novel graph convolution mixed with point cloud deep learning method. In this method, the skinned multi‐person linear model is regarded as a graph structure input, and the coarsened graph is obtained by graph convolution. After feeding the coarsened graph into the PointNet network, the coordinates of Dazhui are output. Different from the existing methods, the proposed method can directly label the results on the adaptive model, thus improving the accuracy on different models. An optimization method based on graph structure is introduced for better fit the predicted acupoints to the surface. In addition, a dataset marked with Dazhui is constructed for training. Experiments show that the accuracy of positioning could meet the requirements of needle application under certain circumstances.

show abstract

“…The parametric reconstruction of a model refers to establishing a mapping and correlations between the input data and the dataset of the given model by using statistical methods and applying the input data as a constraint. This is then used to generate the target model under the corresponding parameters of the dataset of the model, and accordingly altering the shape and posture of the represented body (Chen et al, 2023). The key to this technique is the form of the input, the dataset of the model and the mapping relationship between them.…”

Section: Introductionmentioning

confidence: 99%

Status of research on parametric methods for the reconstruction of 3D models of the human body for virtual fitting

Feng,

Li,

Wang

et al. 2024

IJCST

View full text Add to dashboard Cite

PurposeThis paper reviews the pros and cons of different parametric modeling methods, which can provide a theoretical reference for parametric reconstruction of 3D human body models for virtual fitting.Design/methodology/approachIn this study, we briefly analyze the mainstream datasets of models of the human body used in the area to provide a foundation for parametric methods of such reconstruction. We then analyze and compare parametric methods of reconstruction based on their use of the following forms of input data: point cloud data, image contours, sizes of features and points representing the joints. Finally, we summarize the advantages and problems of each method as well as the current challenges to the use of parametric modeling in virtual fitting and the opportunities provided by it.FindingsConsidering the aspects of integrity and accurate of representations of the shape and posture of the body, and the efficiency of the calculation of the requisite parameters, the reconstruction method of human body by integrating orthogonal image contour morphological features, multifeature size constraints and joint point positioning can better represent human body shape, posture and personalized feature size and has higher research value.Originality/valueThis article obtains a research thinking for reconstructing a 3D model for virtual fitting that is based on three kinds of data, which is helpful for establishing personalized and high-precision human body models.

show abstract

3D human body reconstruction based on SMPL model

Cited by 9 publications

References 49 publications

What's in a Decade? Transforming Faces Through Time

What's in a Decade? Transforming Faces Through Time

Location of acupuncture points based on graph convolution and 3D deep learning in virtual humans

Status of research on parametric methods for the reconstruction of 3D models of the human body for virtual fitting

Contact Info

Product

Resources

About