UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Yan, Haonan; Chen, Jiaqi; Zhang, Xujie; Zhang, Shengkai; Jiao, Nianhong; Liang, Xiaodan; Zheng, Tianxiang

doi:10.1109/iccv48922.2021.01071

Cited by 11 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AGORA training and evaluation dataset has been developed specifically for this purpose, enabling generation of images with diverse movements, environments and cameras angles [47], although it does not yet include biomechanically driven human body models. However, synthetic images using 3D body models have the potential to move beyond sparse pose estimation, as all points on the body are known, potentially facilitating applications of dense pose estimations [55]. Future work is needed to determine the biomechanical accuracy of these synthetic images, especially in the clinical and sporting field where movements are so diverse.…”

Section: Plos Onementioning

confidence: 99%

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications

Wade,

Needham,

Evans

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

This study examined if occluded joint locations, obtained from 2D markerless motion capture (single camera view), produced 2D joint angles with reduced agreement compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias and limits of agreement for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane limits of agreement accounted for 35–46% of total range of motion at the hip and knee, Bland-Altman bias and limits of agreement (-4.6–1.6 ± 3.7–4.2˚) were actually similar to previously reported marker-based error values. This was not true for the ankle, where the limits of agreement (± 12˚) were still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing methods for creating anatomically accurate markerless training data using marker-based motion capture data.

show abstract

Section: Plos Onementioning

confidence: 99%

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications

Wade,

Needham,

Evans

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…In this section, we evaluate proposed KTN on a newly released benchmark, i.e., UltraPose [54]. Currently, this dataset The performance of densepose algorithm is jointly decided by multiple sub-tasks, including body segmentation, surface classification and UV coordinate regression.…”

Section: Appendix C: Comparison With Sotas On Ultraposementioning

confidence: 99%

KTN: Knowledge Transfer Network for Learning Multiperson 2D-3D Correspondences

Wang¹,

Gao²,

Zhou³

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

“…They obtain favourable results using only simulated human UV labels. The intricacy of getting dense and accurately annotated correspondences is further explored in UltraPose [61]. They provide a dense synthetic benchmark focusing on faces, containing around 1.3 billion corresponding points as well as data generation system based on novel decoupling 3D model.…”

Section: Related Workmentioning

confidence: 99%

BodyMap: Learning Full-Body Dense Correspondence Map

Ianina¹,

Sarafianos²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Dense correspondence between humans carries powerful semantic information that can be utilized to solve fundamental problems for full-body understanding such as in-thewild surface matching, tracking and reconstruction. In this paper we present BodyMap, a new framework for obtaining high-definition full-body and continuous dense correspondence between in-the-wild images of clothed humans and the surface of a 3D template model. The correspondences cover fine details such as hands and hair, while capturing regions far from the body surface, such as loose clothing. Prior methods for estimating such dense surface correspondence i) cut a 3D body into parts which are unwrapped to a 2D UV space, producing discontinuities along part seams, or ii) use a single surface for representing the whole body, but none handled body details. Here, we introduce a novel network architecture with Vision Transformers that learn fine-level features on a continuous body surface. BodyMap outperforms prior work on various metrics and datasets, including DensePose-COCO by a large margin. Furthermore, we show various applications ranging from multi-layer dense cloth correspondence, neural rendering with novel-view synthesis and appearance swapping.

show abstract

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Cited by 11 publications

References 20 publications

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications

KTN: Knowledge Transfer Network for Learning Multiperson 2D-3D Correspondences

BodyMap: Learning Full-Body Dense Correspondence Map

Contact Info

Product

Resources

About