Bayesian View Synthesis and Image-Based Rendering Principles - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Bayesian View Synthesis and Image-Based Rendering Principles


In this paper, we address the problem of synthesizing novel views from a set of input images. State of the art methods, such as the Unstructured Lumigraph, have been using heuristics to combine information from the original views, often using an explicit or implicit approximation of the scene geometry. While the proposed heuristics have been largely explored and proven to work effectively, a Bayesian formulation was recently introduced, formalizing some of the previously proposed heuristics, pointing out which physical phenomena could lie behind each. However, some important heuristics were still not taken into account and lack proper formalization. We contribute a new physics-based generative model and the corresponding Maximum a Posteriori estimate, providing the desired unification between heuristics-based methods and a Bayesian formulation. The key point is to systematically consider the error induced by the uncertainty in the geometric proxy. We provide an extensive discussion, analyzing how the obtained equations explain the heuristics developed in previous methods. Furthermore, we show that our novel Bayesian model significantly improves the quality of novel views, in particular if the scene geometry estimate is inaccurate.
Fichier principal
Vignette du fichier
BayesianViewSyntehsis_PUJADES_CVPR14.pdf (211.74 Ko) Télécharger le fichier
Vignette du fichier
BayesianPreviz (1).png (100.15 Ko) Télécharger le fichier
366_PUJADES_SupplementaryMaterial_final.pdf (43.65 Mo) Télécharger le fichier
BayesianPreviz.png (100.15 Ko) Télécharger le fichier
poster_BVS_IBRP.pdf (4.1 Mo) Télécharger le fichier
video-spotlight-O4F4.mp4 (9.26 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Format Figure, Image
Format Other
Format Other
Format Video
Origin Files produced by the author(s)

Dates and versions

hal-00983315 , version 1 (09-02-2015)



Sergi Pujades, Frédéric Devernay, Bastian Goldluecke. Bayesian View Synthesis and Image-Based Rendering Principles. CVPR - 27th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, United States. pp.3906 - 3913, ⟨10.1109/CVPR.2014.499⟩. ⟨hal-00983315⟩
448 View
523 Download



Gmail Mastodon Facebook X LinkedIn More