Finite Aperture Stereo: 3D Reconstruction of Macro-Scale Scenes

Matthew Bailey, Adrian Hilton, Jean-Yves Guillemaut; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 2474-2484

Abstract


While the accuracy of multi-view stereo (MVS) has continued to advance, its performance reconstructing challenging scenes from images with a limited depth of field is generally poor. Typical implementations assume a pinhole camera model, and therefore treat defocused regions as a source of outlier. In this paper, we address these limitations by instead modelling the camera as a thick lens. Doing so allows us to exploit the complementary nature of stereo and defocus information, and overcome constraints imposed by traditional MVS methods. Using our novel reconstruction framework, we recover complete 3D models of complex macro-scale scenes. Our approach demonstrates robustness to view-dependent materials, and outperforms state-of-the-art MVS and depth from defocus across a range of real and synthetic datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Bailey_2021_ICCV, author = {Bailey, Matthew and Hilton, Adrian and Guillemaut, Jean-Yves}, title = {Finite Aperture Stereo: 3D Reconstruction of Macro-Scale Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2021}, pages = {2474-2484} }