Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery

Yu, Zhenbo; Wang, Junjie; Xu, Jingwei; Ni, Bingbing; Zhao, Chenglong; Wang, Minsi; Zhang, Wenjun

doi:10.1109/iccv48922.2021.00850

Cited by 16 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shape and twist angles are learned in a regression-based manner. Differential IK module in [98] relies on a set of kinematics prior knowledge to infer 3D rotations from estimated 3D skeletons.…”

Section: Optimization-based Paradigmmentioning

confidence: 99%

“…Parametric Output. The majority of image-based human mesh recovery methods [16], [17], [18], [19], [20], [25], [37], [94], [97], [98], [99], [100], [101], [102], [103], [104], [105], [106], [107] choose to directly regress the parameters of the parametric models. They are also categorized as "modelbased" approaches.…”

Section: Regression-based Paradigmmentioning

confidence: 99%

“…The prediction of the human model and camera parameters allows us to obtain corresponding 2D joints through re-projection and measure the displacement between ground truth and estimated 2D joints. Results can also benefit from the supervision for silhouettes [36], [98], segmentations [99], [105], [137] and dense correspondences [19], [94], [111], [123]. As pointed out in [136], dense correspondences such as IUV map is an effective substitute for 3D annotations.…”

Section: Regression-based Paradigmmentioning

confidence: 99%

“…Output Type a) Template paramters: [16], [17], [18], [19], [20], [21], [25], [37], [94], [97], [98], [99], [101], [102], [103], [104], [105], [106], [111], [112], [125], [129], [135], [140] b) 3D vertex coordinates: GraphCMR [117], Pose2Mesh [132], I2L-MeshNet [118], PC-HMR [121], METRO [120], Graphormer [119] c) Voxels: BodyNet [115], DeepHuman [116] d) UV position maps: DenseBody [122], DecoMR [123], Zhang et al [124] e) Probabilistic outputs: Biggs et al [125], Sengupta et al [127], [128], ProHMR [126] Intermediate/ Proxy Representation a) Silhouettes: Pavlakos et al [17], STRAPS [103], Skeleton2Mesh [98] b) Segmentations: NBF [18], Rueegg et al [129], STRAPS [103], Zanfir et al [105], HUND…”

Section: Framebased Single Personmentioning

confidence: 99%

“…a) 2D keypoints: [13], [16], [17], [18], [19], [20], [21], [22], [23], [25], [36], [37], [87], [93], [99], [105], [106], [108], [111], [120], [144] b) Silhouettes: Balan et al [82], [88], Sigal et al [152], Guan et al [89], Tung et al [36], Pavlakos et al [17], Zhang et al [124], Skeleton2Mesh [98] c) Segmentations: Lassner et al [35], Zanfir et al [105], PARE [20] d) UV Position Map: DenseBody [122], DecoMR [123], Zhang et al [124] e) IUV: HoloPose [94], Rong et al [136], DenseRac [99], DaNet [111], PyMAF [19] 3D Loss a) Parameters: [16], [17], [18], [19], [20], [21], [22], [23],…”

Section: Alignment 2d Lossmentioning

confidence: 99%

See 4 more Smart Citations

Recovering 3D Human Mesh from Monocular Images: A Survey

Tian¹,

Zhang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Estimating human pose and shape from monocular images is a long-standing problem in computer vision. Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention. With the same goal of obtaining well-aligned and physically plausible mesh results, two paradigms have been developed to overcome challenges in the 2D-to-3D lifting process: i) an optimization-based paradigm, where different data terms and regularization terms are exploited as optimization objectives; and ii) a regression-based paradigm, where deep learning techniques are embraced to solve the problem in an end-to-end fashion. Meanwhile, continuous efforts are devoted to improving the quality of 3D mesh labels for a wide range of datasets. Though remarkable progress has been achieved in the past decade, the task is still challenging due to flexible body motions, diverse appearances, complex environments, and insufficient in-the-wild annotations. To the best of our knowledge, this is the first survey to focus on the task of monocular 3D human mesh recovery. We start with the introduction of body models and then elaborate recovery frameworks and training objectives by providing in-depth analyses of their strengths and weaknesses. We also summarize datasets, evaluation metrics, and benchmark results. Open issues and future directions are discussed in the end, hoping to motivate researchers and facilitate their research in this area. A regularly updated project page can be found at https://github.com/tinatiansjz/hmr-survey.

show abstract

Section: Optimization-based Paradigmmentioning

confidence: 99%