Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Open Access Articles
  3. MIT Open Access Articles
  4. In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks

In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks

Thumbnail Image
Download
Name

1911.11924.pdf

Description
Accepted version
Size

25.92 MB

Format

Adobe PDF

Checksum (MD5)

5c911b373667f0ee1f3e0bf70ea64877

sword-2021-04-16T17:37:06.original.xml (130 B)
Original SWORD entry document
Author(s)
Yang, Heng
•
Carlone, Luca
Date Issued
August 2020
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Yang, Heng and Carlone, Luca. 2020. "In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks." Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
Version
Author's final manuscript
Abstract
© 2020 IEEE We study the problem of 3D shape reconstruction from 2D landmarks extracted in a single image. We adopt the 3D deformable shape model and formulate the reconstruction as a joint optimization of the camera pose and the linear shape parameters. Our first contribution is to apply Lasserre's hierarchy of convex Sums-of-Squares (SOS) relaxations to solve the shape reconstruction problem and show that the SOS relaxation of minimum order 2 empirically solves the original non-convex problem exactly. Our second contribution is to exploit the structure of the polynomial in the objective function and find a reduced set of basis monomials for the SOS relaxation that significantly decreases the size of the resulting semidefinite program (SDP) without compromising its accuracy. These two contributions, to the best of our knowledge, lead to the first certifiably optimal solver for 3D shape reconstruction, that we name Shape#. Our third contribution is to add an outlier rejection layer to Shape# using a truncated least squares (TLS) robust cost function and leveraging graduated non-convexity to solve TLS without initialization. The result is a robust reconstruction algorithm, named Shape#, that tolerates a large amount of outlier measurements. We evaluate the performance of Shape and Shape# in both simulated and real experiments, showing that Shape# outperforms local optimization and previous convex relaxation techniques, while Shape# achieves state-of-the-art performance and is robust against 70% outliers in the FG3DCar dataset.
MIT Department
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
http://creativecommons.org/licenses/by-nc-sa/4.0/
Persistent DSpace Link
https://hdl.handle.net/1721.1/137270
DOI of Published Version
https://doi.org/10.1109/CVPR42600.2020.00070
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.