Hybrid Image-based Rendering
for Free-view Synthesis

Siddhant Prakash Thomas Leimkühler Simon Rodriguez George Drettakis
Université Côte d'Azur and Inria Université Côte d'Azur and Inria Université Côte d'Azur and Inria Université Côte d'Azur and Inria

Paper | Video | Presentation | Code | Publication Page | Supplementals | Datasets


Image-based rendering (IBR) provides a rich toolset for free-viewpoint navigation in captured scenes. Many methods exist, usually with an emphasis either on image quality or rendering speed. In this paper we identify common IBR artifacts and combine the strengths of different algorithms to strike a good balance in the speed/quality tradeoff. First, we address the problem of visible color seams that arise from blending casually-captured input images by explicitly treating view-dependent effects. Second, we compensate for geometric reconstruction errors by refining per-view information using a novel clustering and filtering approach. Finally, we devise a practical hybrid IBR algorithm, which locally identifies and utilizes the rendering method best suited for an image region while retaining interactive rates. We compare our method against classical and modern (neural) approaches in indoor and outdoor scenes and demonstrate superiority in quality and/or speed.


Hybrid Image-based Rendering for Free-View Synthesis pdf


I3D 2021 Presentation


The code is released as a SIBR framework project at: https://gitlab.inria.fr/sibr/projects/hybrid_ibr

Funding and Acknowledgements

The authors would like to thank Peter Hedman and Julien Philip for initial discussions and tests. The research was funded by the ERC Advanced grant FUNGRAPH No 788065. The authors are grateful to Inria Sophia Antipolis - Méditerranée "Nef" computation cluster and the OPAL infrastructure from Université Côte d'Azur for providing resources and support.

Supplemental Materials and Results


All Datasets (147 GB) |

Individual Datasets