Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

Zhou, Xingyi; Huang, Qixing; Sun, Xiao; Xue, Xiangyang; Wei, Yichen

doi:10.1109/iccv.2017.51

Cited by 577 publications

(592 citation statements)

References 39 publications

Supporting

Mentioning

578

Contrasting

Order By: Relevance

“…To leverage such cross-domain shared knowledge, domain adaptation [49,15] has been widely studied on different tasks, such as detection [7,26], classification [19,21,17,16], segmentation [59,54,16] and pose estimation [57,46]. But in previous works about keypoint detection or pose estimation [9,57,53,56], source domain and target domain face much slighter domain shift than when transferring from human dataset to animals or among different animal species. Besides, some extra information might be available for easier knowledge transfer, such as view consistency [57], attribute attached to samples [17] or morphological similarity [53,56].…”

Section: Related Workmentioning

confidence: 99%

Cross-Domain Adaptation for Animal Pose Estimation

Cao

Tang

Fang³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

129

110

View full text Add to dashboard Cite

In this paper, we are interested in pose estimation of animals. Animals usually exhibit a wide range of variations on poses and there is no available animal pose dataset for training and testing. To address this problem, we build an animal pose dataset to facilitate training and evaluation. Considering the heavy labor needed to label dataset and it is impossible to label data for all concerned animal species, we, therefore, proposed a novel cross-domain adaptation method to transform the animal pose knowledge from labeled animal classes to unlabeled animal classes. We use the modest animal pose dataset to adapt learned knowledge to multiple animals species. Moreover, humans also share skeleton similarities with some animals (especially four-footed mammals). Therefore, the easily available human pose dataset, which is of a much larger scale than our labeled animal dataset, provides important prior knowledge to boost up the performance on animal pose estimation. Experiments show that our proposed method leverages these pieces of prior knowledge well and achieves convincing results on animal pose estimation. The built dataset and other resources have been publicly released on www.jinkuncao.com/animalpose.

show abstract

Section: Related Workmentioning

confidence: 99%

Cross-Domain Adaptation for Animal Pose Estimation

Cao

Tang

Fang³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

129

110

View full text Add to dashboard Cite

show abstract

“…We compare our method with both task-oriented 3D pose state of the art [50,62,34,36,37,9,48,60,16] and four parametric body model based estimators [26,22,42,39]. We set up two baselines to validate the effectiveness of two key components in the proposed framework: renderand-compare and joint learning with synthetic data.…”

Section: Pose Estimationmentioning

confidence: 99%

DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare

Zhu

Tung

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

183

112

View full text Add to dashboard Cite

We present DenseRaC, a novel end-to-end framework for jointly estimating 3D human pose and body shape from a monocular RGB image. Our two-step framework takes the body pixel-to-surface correspondence map (i.e., IUV map) as proxy representation and then performs estimation of parameterized human pose and shape. Specifically, given an estimated IUV map, we develop a deep neural network optimizing 3D body reconstruction losses and further integrating a render-and-compare scheme to minimize differences between the input and the rendered output, i.e., dense body landmarks, body part masks, and adversarial priors. To boost learning, we further construct a large-scale synthetic dataset (MOCA) utilizing web-crawled Mocap sequences, 3D scans and animations. The generated data covers diversified camera views, human actions and body shapes, and is paired with full ground truth. Our model jointly learns to represent the 3D human body from hybrid datasets, mitigating the problem of unpaired training data. Our experiments show that DenseRaC obtains superior performance against state of the art on public benchmarks of various humanrelated tasks.

show abstract

“…Weak supervision provided by 2D annotations is typical, with different works employing 2D keypoints, silhouettes and semantic parts [18,31,35,46]. Non-parametric approaches typically use extra supervision from 2D keypoint annotation [12,45,55], while some recent works leverage ordinal depth relations of the joints [33,41]. Multi-view consistency is also well explored as discussed earlier [21,34,38,39,44].…”

Section: Related Workmentioning

confidence: 99%

TexturePose: Supervising Human Mesh Estimation With Texture Consistency

Pavlakos

Kolotouros

Daniilidis

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

123

View full text Add to dashboard Cite

This work addresses the problem of model-based human pose estimation. Recent approaches have made significant progress towards regressing the parameters of parametric human body models directly from images. Because of the absence of images with 3D shape ground truth, relevant approaches rely on 2D annotations or sophisticated architecture designs. In this work, we advocate that there are more cues we can leverage, which are available for free in natural images, i.e., without getting more annotations, or modifying the network architecture. We propose a natural form of supervision, that capitalizes on the appearance constancy of a person among different frames (or viewpoints). This seemingly insignificant and often overlooked cue goes a long way for model-based pose estimation. The parametric model we employ allows us to compute a texture map for each frame. Assuming that the texture of the person does not change dramatically between frames, we can apply a novel texture consistency loss, which enforces that each point in the texture map has the same texture value across all frames. Since the texture is transferred in this common texture map space, no camera motion computation is necessary, or even an assumption of smoothness among frames. This makes our proposed supervision applicable in a variety of settings, ranging from monocular video, to multi-view images. We benchmark our approach against strong baselines that require the same or even more annotations that we do and we consistently outperform them. Simultaneously, we achieve state-of-the-art results among model-based pose estimation approaches in different benchmarks. The project website with videos, results, and code can be found at https: //seas.upenn.edu/˜pavlakos/projects/texturepose.

show abstract

Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

Cited by 577 publications

References 39 publications

Cross-Domain Adaptation for Animal Pose Estimation

Cross-Domain Adaptation for Animal Pose Estimation

DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare

TexturePose: Supervising Human Mesh Estimation With Texture Consistency

Contact Info

Product

Resources

About