Parametric 3D Visualization Modeling of the Human Body Based on 2D Photos

Lu, Meijuan; Zhang, Jiaming; Tang, Lei; Wei, Hongtao

doi:10.1109/icbaie52039.2021.9389918

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Orthographic images. Compared with a single image, orthogonal images can better express information on the shape of the front and side contours of the human body (Lu et al, 2021). Song established a mapping function between the binary map of the orthogonal contours and the corresponding 2D landmarks of the human body and used it to predict 3D landmarks in new data.…”

Section: Model Reconstruction Based On Image Contoursmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Model Reconstruction Based On Image Contoursmentioning

confidence: 99%

“…Compared with a single image, orthogonal images can better express information on the shape of the front and side contours of the human body (Lu et al. , 2021).…”

Section: Parametric Reconstruction Of 3d Model Of the Human Bodymentioning

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

show abstract

“…The approach holds promise for various applications, including human body modeling for different fields. [13] The article offers Self-Supervision Text-to-Image Generative Adversarial Networks (SS-TiGAN), a revolutionary text-to-image synthesis technique. To address issues in low-data regimes and improve the quality and diversity of synthesized images, the technique combines self-supervision and a bi-level GAN architecture.…”

Section: Dataset Descriptionmentioning

confidence: 99%

Brain to 3D Model (Enabling tech of 3D Printers)

Abdullah Bin Masood,

Muhammad Javaid Iqbal,

Sheeraz Akram

et al. 2024

JICET

View full text Add to dashboard Cite

This study was planned to conduct and to bring the novel approach of thoughts into 3D into reality by using AI techniques & Methods. The study was conducted on user EEG signals and processed into pre-trained tokens of NLP and EEG signals to identify the probability of the EEG signal approach. The translation of EEG and ECoG signals into NLP level and generate a better prompting to Solve the issue hidden in Tokens of Prompting. These Prompt Techniques produce Generative Art by using Stable diffusion to create an image. That 2 Dimension image has Raw data at the background which is removed by using u2net & ModNet to introduce a more refined format as a preprocess for 3-D artwork Generation. The study focused on using different model like shape-e by OpenAI to create a more general approach but our code used it to produce for specifically 3-D avatar character for Metaverse. Using PifuHD estimation model by Facebook and lightweight human pose estimation.3-D art produced a more refined artwork as 3-D object file that can later be used in terms of producing into 3-D printed stuff and enable 3-D Printers closer to User Access as an efficient way of Technology.

show abstract

Parametric 3D Visualization Modeling of the Human Body Based on 2D Photos

Cited by 2 publications

References 19 publications

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

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

Brain to 3D Model (Enabling tech of 3D Printers)

Contact Info

Product

Resources

About