mlsanityData to 7 Oct 2026

High Fidelity 3D Reconstructions with Limited Physical Views

arXiv 2110.11599 ↗First posted 22 Oct 2021cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Multi-view triangulation is the gold standard for 3D reconstruction from 2D correspondences given known calibration and sufficient views. However in practice, expensive multi-view setups -- involving tens sometimes hundreds of cameras -- are required in order to obtain the high fidelity 3D reconstructions necessary for many modern applications. In this paper we present a novel approach that leverages recent advances in 2D-3D lifting using neural shape priors while also enforcing multi-view equivariance. We show how our method can achieve comparable fidelity to expensive calibrated multi-view rigs using a limited (2-3) number of uncalibrated camera views.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 54 references that are in the map. First posted on arXiv 22 Oct 2021.

Builds on

27 of 54 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  6. 2017Integral Human Pose Regressioncited by 255
  7. 2019Learnable Triangulation of Human Posecited by 160
  8. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  9. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  10. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  11. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  12. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 60
15 more
  1. 2020Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representationcited by 57
  2. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  3. 2016Convolutional Neural Networks Analyzed via Convolutional Sparse Codingcited by 51
  4. 2017Harvesting Multiple Views for Marker-less 3D Human Pose Annotationscited by 48
  5. 2019Deep Non-Rigid Structure from Motioncited by 38
  6. 2020RGBD-Dog: Predicting Canine Pose from RGBD Sensorscited by 35
  7. 2018A generalizable approach for multi-view 3D human pose regressioncited by 26
  8. 2019Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scenecited by 22
  9. 2018Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locationscited by 18
  10. 2019Non-Rigid Structure from Motion: Prior-Free Factorization Method Revisitedcited by 18
  11. 2018Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capturecited by 17
  12. 2018A Benchmark and Evaluation of Non-Rigid Structure from Motioncited by 14
  13. 2016Multi-body Non-rigid Structure-from-Motioncited by 13
  14. 2020Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D Annotationscited by 13
  15. 2020Deep NRSfM++: Towards Unsupervised 2D-3D Lifting in the Wildcited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.

  1. 20233D-LFM: Lifting Foundation Modelcited by 8
  2. 2022MBW: Multi-view Bootstrapping in the Wildcited by 1