Online Projector Deblurring Using a Convolutional Neural Network

Shadowless Projection Mapping using Retrotransmissive Optics

“…Therefore, this result supports our hypothesis. Second, we validated the effectiveness of the CNN-based blur compensation technique [25] on the projected image quality in our system. We used the network and learned parameters of [25] without fine-tuning.…”

“…Second, we validated the effectiveness of the CNN-based blur compensation technique [25] on the projected image quality in our system. We used the network and learned parameters of [25] without fine-tuning. We used both the tilted square plane and the 3D-printed Stanford bunny as the target objects.…”

“…In principle, the current retrotransmissive devices cannot make a point light source converge to a single point at the plane-symmetrical positions, and thus, the projected result becomes blurred. In this work, we demonstrate that the blur can be alleviated by applying a defocus blur compensation technique [25] that computationally corrects projection images using a convolutional neural network (CNN).…”

“…We decide to use a CNN-based defocus blur compensation technique [24,25] for the following two reasons. First, CNN-based techniques do not require explicit estimation of the point spread function (PSF), which is generally performed by projecting artificial dot patterns, and thus, significantly degrades the user experience.…”

Focal surface projection: Extending projector depth of field using a phase‐only spatial light modulator

“…Most single‐projector techniques sharpen the original images such that the projected results look similar to the original ones. This pre‐sharpening is realized using the Wiener filter, 5,6 constrained optimization, 7,8 or deep neural networks 9,10 . Although these methods significantly reduce the defocus blur, the pre‐sharpening process introduces ringing artifacts in the projected result when the point spread function (PSF) of a projected pixel cuts a large number of high‐spatial‐frequency components 11 .…”