paper-with-me

Papers

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

2018-04-03 · ECCV 2018 9 · Helge Rhodin, Mathieu Salzmann, Pascal Fua

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed. In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Because this representation encodes 3D geometry, using it in a semi-supervised setting makes it easier to learn a mapping from it to 3D human pose. As evidenced by our experiments, our approach significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-supervised methods while using as little as 1% of the labeled data.

📄 PDF Abstract BibTeX arXiv:1804.01110

Code (2)

hrhodin/UnsupervisedGeometryAwareRepresentationLearning pytorch
mattiagaggi/3D-Pose-Estimator---MSc_project pytorch

Tasks

3D geometry3D Human Pose EstimationDecoderPose EstimationWeakly-supervised 3D Human Pose Estimation

Similar Papers 제목 키워드 기반

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

2019-06-04 · NeurIPS 2019 12 · Vincent Sitzmann, Michael Zollhöfer, Gordon Wetzstein

Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes. While geometric deep learning has explored 3D-structure-aware representations of scene geometry, these mode…

Face ModelNovel View Synthesis

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

2022-04-19 · Atsuhiro Noguchi, Xiao Sun, Stephen Lin, Tatsuya Harada

We propose an unsupervised method for 3D geometry-aware representation learning of articulated objects, in which no image-pose pairs or foreground masks are used for training. Though photorealistic images of articulated …

3D geometryRepresentation Learning

AvatarGen: A 3D Generative Model for Animatable Human Avatars

2022-11-26 · Jianfeng Zhang, Zihang Jiang, Dingdong Yang, Hongyi Xu 외

Unsupervised generation of 3D-aware clothed humans with various appearances and controllable geometries is important for creating virtual human avatars and other AR/VR applications. Existing methods are either limited to…

Human Animation

PartGS:Learning Part-aware 3D Representations by Fusing 2D Gaussians and Superquadrics

2024-08-20 · Zhirui Gao, Renjiao Yi, Yuhang Huang, Wei Chen 외

Low-level 3D representations, such as point clouds, meshes, NeRFs, and 3D Gaussians, are commonly used to represent 3D objects or scenes. However, human perception typically understands 3D objects at a higher level as a …

3D Reconstruction

GARF:Geometry-Aware Generalized Neural Radiance Field

2022-12-05 · Yue Shi, Dingyi Rong, Bingbing Ni, Chang Chen 외

Neural Radiance Field (NeRF) has revolutionized free viewpoint rendering tasks and achieved impressive results. However, the efficiency and accuracy problems hinder its wide applications. To address these issues, we prop…

3D geometryDecoderDepth EstimationNeRF+2