DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields

TL;DR

DoF-NeRF extends neural radiance fields to handle images with finite depth-of-field, enabling realistic DoF effects and focus manipulation while maintaining high-quality novel view synthesis.

Contribution

It introduces a physically grounded aperture modeling into NeRF, allowing simulation and manipulation of depth-of-field effects in neural rendering.

Findings

Performs comparably to NeRF on all-in-focus data

Successfully synthesizes novel views with shallow DoF inputs

Enables explicit control over DoF parameters

Abstract

Neural Radiance Field (NeRF) and its variants have exhibited great success on representing 3D scenes and synthesizing photo-realistic novel views. However, they are generally based on the pinhole camera model and assume all-in-focus inputs. This limits their applicability as images captured from the real world often have finite depth-of-field (DoF). To mitigate this issue, we introduce DoF-NeRF, a novel neural rendering approach that can deal with shallow DoF inputs and can simulate DoF effect. In particular, it extends NeRF to simulate the aperture of lens following the principles of geometric optics. Such a physical guarantee allows DoF-NeRF to operate views with different focus configurations. Benefiting from explicit aperture modeling, DoF-NeRF also enables direct manipulation of DoF effect by adjusting virtual aperture and focus parameters. It is plug-and-play and can be inserted into NeRF-based frameworks. Experiments on synthetic and real-world datasets show that, DoF-NeRF not only performs comparably with NeRF in the all-in-focus setting, but also can synthesize all-in-focus novel views conditioned on shallow DoF inputs. An interesting application of DoF-NeRF to DoF rendering is also demonstrated. The source code will be made available at https://github.com/zijinwuzijin/DoF-NeRF.