Deep unsupervised 3D human body reconstruction from a sparse set of landmarks
Not on the map. Why?
Abstract (arXiv)
In this paper we propose the first deep unsupervised approach in human body reconstruction to estimate body surface from a sparse set of landmarks, so called DeepMurf. We apply a denoising autoencoder to estimate missing landmarks. Then we apply an attention model to estimate body joints from landmarks. Finally, a cascading network is applied to regress parameters of a statistical generative model that reconstructs body. Our set of proposed loss functions allows us to train the network in an unsupervised way. Results on four public datasets show that our approach accurately reconstructs the human body from real world mocap data.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 38 references that are in the map. First posted on arXiv 23 Jun 2021.
Builds on
20 of 38 references.
References · 20
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
- 2017End-to-end Recovery of Human Shape and Posecited by 885
- 2017Learning from Synthetic Humanscited by 359
- 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
- 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
- 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
- 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
- 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
- 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
- 2017Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUscited by 109
- 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
- 2019Efficient Learning on Point Clouds with Basis Point Setscited by 103
8 more
- 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
- 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
- 2019XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Cameracited by 68
- 2018Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Timecited by 47
- 2018Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locationscited by 18
- 2016General Automatic Human Shape and Motion Capture Using Volumetric Contour Cuescited by 15
- 2018Toward Marker-free 3D Pose Estimation in Lifting: A Deep Multi-view Solutioncited by 5
- 2018SMPLR: Deep SMPL reverse for 3D human pose and shape recoverycited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.