DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields
This addresses a practical problem for 3D scene rendering applications where real-world images often have finite DoF, though it is an incremental extension of existing NeRF frameworks.
The paper tackles the limitation of Neural Radiance Fields (NeRF) in handling shallow depth-of-field (DoF) inputs by introducing DoF-NeRF, which extends NeRF to simulate lens aperture based on geometric optics, enabling synthesis of all-in-focus novel views from DoF inputs and direct manipulation of DoF effects.
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.