Lens Parameter Estimation for Realistic Depth of Field Modeling

Dominique Piché-Meunier, Yannick Hold-Geoffroy, Jianming Zhang, Jean-François Lalonde; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 499-508

Abstract


We present a method to estimate the depth of field effect from a single image. Most existing methods related to this task provide either a per-pixel estimation of blur and/or depth. Instead, we go further and propose to use a lens-based representation that models the depth of field using two parameters: the blur factor and focus disparity. Those two parameters, along with the signed defocus representation, result in a more intuitive and linear representation which we solve using a novel weighting network. Furthermore, our method explicitly enforces consistency between the estimated defocus blur, the lens parameters, and the depth map. Finally, we train our deep-learning-based model on a mix of real images with synthetic depth of field and fully synthetic images. These improvements result in a more robust and accurate method, as demonstrated by our state-of-the-art results. In particular, our lens parametrization enables several applications, such as 3D staging for AR environments and seamless object compositing.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Piche-Meunier_2023_ICCV, author = {Pich\'e-Meunier, Dominique and Hold-Geoffroy, Yannick and Zhang, Jianming and Lalonde, Jean-Fran\c{c}ois}, title = {Lens Parameter Estimation for Realistic Depth of Field Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {499-508} }