Multi-Garment Net: Learning to Dress 3D People From Images

Bhatnagar, Bharat Lal; Tiwari, Garvita; Theobalt, Christian; Pons-Moll, Gerard

doi:10.1109/iccv.2019.00552

Cited by 349 publications

(150 citation statements)

References 64 publications

Supporting

Mentioning

150

Contrasting

Order By: Relevance

“…Even simple architectures have been shown to solve this task with a low error rate [15]. Recent advances are due to combining the 2D and 3D tasks into a joint estimation [4], [32], [33], [34] and using weakly [35], [36], [37], [38], [39] or self-supervised losses [40], [41], [42], [43], [44] or mixing 2D and 3D data for training [6], [42], [45], [46].…”

Section: Monocular 3d Pose Estimation From An External Cameramentioning

confidence: 99%

SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera

Tomè

Alldieck

Peluse

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

We present a new solution to egocentric 3D body pose estimation from monocular images captured from a downward looking fish-eye camera installed on the rim of a head mounted virtual reality device. This unusual viewpoint leads to images with unique visual appearance, characterized by severe self-occlusions and strong perspective distortions that result in a drastic difference in resolution between lower and upper body. We propose a new encoder-decoder architecture with a novel multi-branch decoder designed specifically to account for the varying uncertainty in 2D joint locations. Our quantitative evaluation, both on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric pose estimation approaches. To tackle the severe lack of labelled training data for egocentric 3D pose estimation we also introduced a large-scale photo-realistic synthetic dataset. xR-EgoPose offers 383K frames of high quality renderings of people with diverse skin tones, body shapes and clothing, in a variety of backgrounds and lighting conditions, performing a range of actions. Our experiments show that the high variability in our new synthetic training corpus leads to good generalization to real world footage and to state of the art results on real world datasets with ground truth. Moreover, an evaluation on the Human3.6M benchmark shows that the performance of our method is on par with top performing approaches on the more classic problem of 3D human pose from a third person viewpoint.

show abstract

Section: Monocular 3d Pose Estimation From An External Cameramentioning

confidence: 99%

SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera

Tomè

Alldieck

Peluse

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Note that the ClothCap method uses a sequence of scan data to increase the robustness of labelling, while ours uses only single scan data. As shown in Figure 16, the work of [BTTPM19] greatly improved the quality of the MRF-based segmentation by combining with semantic image segmentation. However, it still shows a few incomplete segmentations in the published dataset.…”

Section: Resultsmentioning

confidence: 99%

“…This method defines weak priors on the surface that are likely to belong to a certain class, and then solves the Markov Random Field (MRF) to perform the segmentation. The work of [BTTPM19] builds upon this approach by additionally incorporating image-based semantic segmentation [GLL*18] into the pipeline. The techniques mentioned above show overall robust segmentation in their applicable scopes; however, since they use independent per-vertex prediction, segmentation is oftentimes noisy, especially on the boundaries between classes.…”

Section: Garment Segmentation On 3d Human Scansmentioning

confidence: 99%

“…Figure 16 compares our method with a geometric garment deformation scheme that represents the garment shape as a displacement from the body mesh and applies linear blend skinning to the garment vertices with the skinning weights of the associated body vertices as detailed in Section 3.1 in [BTTPM19]. Subjects o and q in Figure 16 show unnatural garment deformation around the shoulder and elbow due to this geometric deformation scheme.…”

Section: Comparison With Displacement-based Geometric Deformationmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Garment Patterns from Static Scan Data

Bang

Korosteleva

Lee

2021

Computer Graphics Forum

View full text Add to dashboard Cite

The acquisition of highly detailed static 3D scan data for people in clothing is becoming widely available. Since 3D scan data is given as a single mesh without semantic separation, in order to animate the data, it is necessary to model shape and deformation behaviour of individual body and garment parts. This paper presents a new method for generating simulation-ready garment models from 3D static scan data of clothed humans. A key contribution of our method is a novel approach to segmenting garments by finding optimal boundaries between the skin and garment. Our boundary-based garment segmentation method allows for stable and smooth separation of garments by using an implicit representation of the boundary and its optimization strategy. In addition, we present a novel framework to construct a 2D pattern from the segmented garment and place it around the body for a draping simulation. The effectiveness of our method is validated by generating garment patterns for a number of scan data.

show abstract

“…Physical simulation working within the fashion domain focus on clothing-body interactions, and datasets can be categorized into real data and created data. Despite the rapid revolution on previous datasets which are based on 2D images like DeepFashion [72], DeepFashion2 [77] and FashionAI [116], the production of datasets basing on 3D clothing is almost rare or not sufficient for training like the digital wardrobe released by MGN [117]. In 2020, Heming et al [118] develop a comprehensive dataset named Deep Fashion3D which is richly annotated and covers a much larger variations of garment styles.…”

Section: Video Sequencesmentioning

confidence: 99%

You can Try without Visiting: A Comprehensive Survey on Virtually Try-on Outfits

Ghodhbani¹,

Alimi²,

Néji³

et al. 2021

Preprint

View full text Add to dashboard Cite

<p>Our work aims to conduct a comprehensive literature review of deep learning methods applied in the fashion industry and, especially, the image-based virtual fitting task by citing research works published in the last years. We have summarized their challenges, their main frameworks, the popular benchmark datasets, and the different evaluation metrics. Also, some promising future research directions are discussed to propose improvements in this research field.</p>

show abstract

Multi-Garment Net: Learning to Dress 3D People From Images

Cited by 349 publications

References 64 publications

SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera

SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera

Estimating Garment Patterns from Static Scan Data

You can Try without Visiting: A Comprehensive Survey on Virtually Try-on Outfits

Contact Info

Product

Resources

About