mlsanityData to 14 Oct 2026

MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views

arXiv 2207.09086 ↗First posted 19 Jul 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion (NRSfM). MHR-Net aims to find a set of reasonable reconstructions for a 2D view, and it also selects the most likely reconstruction from the set. To deal with the challenging unsupervised generation of non-rigid shapes, we develop a new Deterministic Basis and Stochastic Deformation scheme in MHR-Net. The non-rigid shape is first expressed as the sum of a coarse shape basis and a flexible shape deformation, then multiple hypotheses are generated with uncertainty modeling of the deformation part. MHR-Net is optimized with reprojection loss on the basis and the best hypothesis. Furthermore, we design a new Procrustean Residual Loss, which reduces the rigid rotations between similar shapes and further improves the performance. Experiments show that MHR-Net achieves state-of-the-art reconstruction accuracy on Human3.6M, SURREAL and 300-VW datasets.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 21 of its 70 references that are in the map. First posted on arXiv 19 Jul 2022.

Builds on

21 of 70 references.

References · 21

  1. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 525
  2. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  3. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  4. 2017Learning from Synthetic Humanscited by 359
  5. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 97
  6. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  7. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  8. 2016Stochastic Multiple Choice Learning for Training Diverse Deep Ensemblescited by 77
  9. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  10. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 61
  11. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  12. 2018Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspectivecited by 19
9 more
  1. 2018Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locationscited by 18
  2. 2019Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learningcited by 13
  3. 2020Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D Annotationscited by 13
  4. 2019Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure from Motioncited by 12
  5. 2020Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimationcited by 10
  6. 2021PAUL: Procrustean Autoencoder for Unsupervised Liftingcited by 9
  7. 2021PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motioncited by 9
  8. 2020Accurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from Motioncited by 5
  9. 2018Incremental Non-Rigid Structure-from-Motion with Unknown Focal Lengthcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 1; 2026: 1.

7 papers.

  1. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  2. 20233D-LFM: Lifting Foundation Modelcited by 8
  3. 2023Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modelingcited by 7
  4. 2024PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modelingcited by 3
  5. 2024Non-rigid Structure-from-Motion: Temporally-smooth Procrustean Alignment and Spatially-variant Deformation Modelingcited by 0
  6. 2025Unsupervised 2D-3D lifting of non-rigid objects using local constraintscited by 0
  7. 2026SSR: A Training-Free Approach for Streaming 3D Reconstructioncited by 0