A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation

Helge Rhodin, Nadia Robertini, Christian Richardt, H.-P. Seidel, Christian Theobalt

Research output: Chapter in Book/Report/Conference proceedingChapter

23 Citations (Scopus)
102 Downloads (Pure)

Abstract

Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the visibility function that indicates if a surface point is seen from a camera can often not be formulated in closed form, and is in general discrete and non-differentiable at occlusion boundaries. We present a new scene representation that enables an analytically differentiable closed-form formulation of surface visibility. In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally verified improved convergence of numerical optimization. The underlying idea is a new image formation model that represents opaque objects by a translucent medium with a smooth Gaussian density distribution which turns visibility into a smooth phenomenon. We demonstrate the advantages of our versatile scene model in several generative pose estimation problems, namely marker-less multi-object pose estimation, marker-less human motion capture with few cameras, and image-based 3D geometry estimation.
Original languageEnglish
Title of host publication2015 IEEE International Conference on Computer Vision (ICCV)
Place of PublicationLos Alamitos, CA, USA
PublisherIEEE
Pages765-773
Number of pages9
ISBN (Print)978-1-4673-8390-5
DOIs
Publication statusPublished - 13 Dec 2015
EventIEEE International Conference on Computer Vision (ICCV 2015) - , UK United Kingdom
Duration: 13 Dec 2015 → …

Publication series

NameIEEE International Conference on Computer Vision (ICCV)
PublisherIEEE
ISSN (Print)2380-7504

Conference

ConferenceIEEE International Conference on Computer Vision (ICCV 2015)
CountryUK United Kingdom
Period13/12/15 → …

Fingerprint Dive into the research topics of 'A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimation'. Together they form a unique fingerprint.

Cite this