SMPL: A Skinned Multi-Person Linear Model

Loper, Margaret L.; Mahmood, Naureen; Romero, Javier; Pons-Moll, Gerard; Black, Michael J.

doi:10.1145/3596711.3596800

Cited by 137 publications

(125 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of human statistical models like SCAPE [9], SMPL [10], SMPLX [11] and Star [12], parametric body estimation from a single image has attracted a lot of attention recently. Methods optimise the shape and pose parameters by fitting the SMPL model to the 2D keypoint detections [13,14] and other dense shape cues [15].…”

Section: Parametric Body Estimation From a Single Imagementioning

confidence: 99%

Skeleton‐aware implicit function for single‐view human reconstruction

Liu

Zhang

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

The aim is to reconstruct a complete and detailed clothed human from a single-view input. Implicit function is suitable for this task because it represents fine shape details and varied topology. Current methods, however, often suffer from artefacts such as broken or disembodied body parts, missing details, or depth ambiguity due to the ambiguity and complexity of human articulation. The main issue observed by the authors is structureagnostic. To address these problems, the authors fully utilise the skinned multi-person linear (SMPL) model and propose a method using the Skeleton-aware Implicit Function (SIF). To alleviate the broken or disembodied body parts, the proposed skeleton-aware structure prior makes the skeleton awareness into an implicit function, which consists of a bone-guided sampling strategy and a skeleton-relative encoding strategy. To deal with the missing details and depth ambiguity problems, the authors' body-guided pixel-aligned feature exploits the SMPL to enhance 2D normal and depth semantic features, and the proposed feature aggregation uses the extra geometry-aware prior to enabling a more plausible merging with less noisy geometry. Additionally, SIF is also adapted to the RGB-D input, and experimental results show that SIF outperforms the state-of-the-arts methods on challenging datasets from Twindom and Thuman3.0.

show abstract

Section: Parametric Body Estimation From a Single Imagementioning

confidence: 99%

Skeleton‐aware implicit function for single‐view human reconstruction

Liu

Zhang

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

“…The Virtual Caliper (Pujades et al 2019) presented an easyto-use framework to rapidly generate avatars that fit the shape of the user. They use the HTC VIVE wand controllers to take measurements of the user, and then they verify that they are linearly related to 3D body shapes from the SMPL body model (Loper et al 2015). But even if the size of the avatar is correct in terms of the width of arms, legs, torso, etc., it does not guarantee that the positions of the avatar's joints match those of the user, and this has a direct impact on achieving realistic positioning of limbs during motion.…”

Section: Character Generationmentioning

confidence: 99%

Fitted avatars: automatic skeleton adjustment for self-avatars in virtual reality

et al. 2023

View full text Add to dashboard Cite

In the era of the metaverse, self-avatars are gaining popularity, as they can enhance presence and provide embodiment when a user is immersed in Virtual Reality. They are also very important in collaborative Virtual Reality to improve communication through gestures. Whether we are using a complex motion capture solution or a few trackers with inverse kinematics (IK), it is essential to have a good match in size between the avatar and the user, as otherwise mismatches in self-avatar posture could be noticeable for the user. To achieve such a correct match in dimensions, a manual process is often required, with the need for a second person to take measurements of body limbs and introduce them into the system. This process can be time-consuming, and prone to errors. In this paper, we propose an automatic measuring method that simply requires the user to do a small set of exercises while wearing a Head-Mounted Display (HMD), two hand controllers, and three trackers. Our work provides an affordable and quick method to automatically extract user measurements and adjust the virtual humanoid skeleton to the exact dimensions. Our results show that our method can reduce the misalignment produced by the IK system when compared to other solutions that simply apply a uniform scaling to an avatar based on the height of the HMD, and make assumptions about the locations of joints with respect to the trackers.

show abstract

“…Synthetic data is a low-cost alternative to generate data with ground truth annotations with minimum effort. Recently, works on human [17,10,30] and animal pose [4,22,16,6,3,2,25,36,35,28] estimation have adopted synthetic data to overcome the scarcity of keypoint labels.…”

Section: Animal Pose Estimation With Synthetic Datamentioning

confidence: 99%

Self-supervised 3D Human Pose Estimation from a Single Image

Sosa,

Hogg

2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Obtaining labelled data to train deep learning methods for estimating animal pose is challenging. Recently, synthetic data has been widely used for pose estimation tasks, but most methods still rely on supervised learning paradigms utilising synthetic images and labels. Can training be fully unsupervised? Is a tiny synthetic dataset sufficient? What are the minimum assumptions that we could make for estimating animal pose? Our proposal addresses these questions through a simple yet effective selfsupervised method that only assumes the availability of unlabelled images and a small set of synthetic 2D poses. We completely remove the need for any 3D or 2D pose annotations (or complex 3D animal models), and surprisingly our approach can still learn accurate 3D and 2D poses simultaneously. We train our method with unlabelled images of horses mainly collected for YouTube videos and a prior consisting of 2D synthetic poses. The latter is three times smaller than the number of images needed for training. We test our method on a challenging set of horse images and evaluate the predicted 3D and 2D poses. We demonstrate that it is possible to learn accurate animal poses even with as few assumptions as unlabelled images and a small set of 2D poses generated from synthetic data. Given the minimum requirements and the abundance of unlabelled data, our method could be easily deployed to different animals.

show abstract

SMPL: A Skinned Multi-Person Linear Model

Cited by 137 publications

References 19 publications

Skeleton‐aware implicit function for single‐view human reconstruction

Skeleton‐aware implicit function for single‐view human reconstruction

Fitted avatars: automatic skeleton adjustment for self-avatars in virtual reality

Self-supervised 3D Human Pose Estimation from a Single Image

Contact Info

Product

Resources

About