Multi-View Dynamic Shape Refinement Using Local Temporal Integration - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Multi-View Dynamic Shape Refinement Using Local Temporal Integration

Vincent Leroy
Edmond Boyer

Résumé

We consider 4D shape reconstructions in multi-view environments and investigate how to exploit temporal redundancy for precision refinement. In addition to being beneficial to many dynamic multi-view scenarios this also enables larger scenes where such increased precision can compensate for the reduced spatial resolution per image frame. With precision and scalability in mind, we propose a symmetric (non-causal) local time-window geometric integration scheme over temporal sequences, where shape reconstructions are refined framewise by warping local and reliable geometric regions of neighboring frames to them. This is in contrast to recent comparable approaches targeting a different context with more compact scenes and real-time applications. These usually use a single dense volumetric update space or geometric template, which they causally track and update globally frame by frame, with limitations in scalability for larger scenes and in topology and precision with a template based strategy. Our templateless and local approach is a first step towards temporal shape super-resolution. We show that it improves reconstruction accuracy by considering multiple frames. To this purpose, and in addition to real data examples, we introduce a multi-camera synthetic dataset that provides ground-truth data for mid-scale dynamic scenes.
Fichier principal
Vignette du fichier
paper_final.pdf (19.4 Mo) Télécharger le fichier
Vignette du fichier
test_banner_specular.jpg (162.38 Ko) Télécharger le fichier
1361-supp.mp4 (31.51 Mo) Télécharger le fichier
ICCV_Supplementary.mp4 (29.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01567758 , version 1 (31-07-2017)
hal-01567758 , version 2 (29-08-2017)

Identifiants

  • HAL Id : hal-01567758 , version 1

Citer

Vincent Leroy, Jean-Sébastien Franco, Edmond Boyer. Multi-View Dynamic Shape Refinement Using Local Temporal Integration. IEEE, International Conference on Computer Vision 2017, Oct 2017, Venice, Italy. ⟨hal-01567758v1⟩
1438 Consultations
791 Téléchargements

Partager

Gmail Facebook X LinkedIn More