A Unified Approach of Multi-scale Deep and Hand-Crafted Features for Defocus Estimation

Park, Jinsun; Tai, Yu-Wing; Cho, Donghyeon; Kweon, In So

doi:10.1109/cvpr.2017.295

Cited by 110 publications

(112 citation statements)

References 39 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…salient bokeh regions) in their dataset. Park et al[2017] combines hand-crafted features with deep features to render refocusable images. However, they focus on noticeable defocus that is generated by medium-large aperture sizes.…”

Section: Synthetic Defocusmentioning

confidence: 99%

Synthetic defocus and look-ahead autofocus for casual videography

et al. 2019

View full text Add to dashboard Cite

In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often crave cinematic focus, but fail to achieve it. We either sacrifice shallow DOF, as in smartphone videos; or we struggle to deliver accurate focus, as in videos from larger cameras. This paper is about a new approach in the pursuit of cinematic focus for casual videography. We present a system that synthetically renders refocusable video from a deep DOF video shot with a smartphone, and analyzes future video frames to deliver context-aware autofocus for the current frame. To create refocusable video, we extend recent machine learning methods designed for still photography, contributing a new dataset for machine training, a rendering model better suited to cinema focus, and a filtering solution for temporal coherence. To choose focus accurately for each frame, we demonstrate autofocus that looks at upcoming video frames and applies AI-assist modules such as motion, face, audio and saliency detection. We also show that autofocus benefits from machine learning and a large-scale video dataset with focus annotation, where we use our RVR-LAAF GUI to create this sizable dataset efficiently. We deliver, for example, a shallow DOF video where the autofocus transitions onto each person before she begins to speak. This is impossible for conventional camera autofocus because it would require seeing into the future.

show abstract

Section: Synthetic Defocusmentioning

confidence: 99%

Synthetic defocus and look-ahead autofocus for casual videography

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Convolutional neural network based approaches have recently gained popularity for blur and defocus estimation from a single image (Suzuki et al, 2003, Park et al, 2017, Anwar et al, 2017.…”

Section: Blur Estimationmentioning

confidence: 99%

Image Sharpening With Blur Map Estimation Using Convolutional Neural Network

Nasonov

Krylov

Lyukov

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> We propose a method for choosing optimal values of the parameters of image sharpening algorithm for out-of-focus blur based on grid warping approach. The idea of the considered sharpening algorithm is to move pixels from the edge neighborhood towards the edge centerlines. Compared to traditional deblurring algorithms, this approach requires only scalar blur level value rather than a blur kernel. We propose a convolutional neural network based algorithm for estimating the blur level value.</p>

show abstract

“…More recently, supervised learning-based approaches [25], and particularly those based on the use of Convolutional Neural Networks (CNN), have shown enormous potential for tackling tasks that require a dense, per-pixel prediction, such as semantic segmentation [27,28], instance segmentation [29] or crowd counting via density map estimation [30]. Blur segmentation can also be viewed as one of such dense prediction tasks, and several works have already explored this approach, either for predicting both types [31,1,32] or defocus only blur [33,34,35,36]. Nevertheless, the performance gain obtained by these fully-supervised, CNN-based approaches trained end-toend is relatively modest when compared to gains in other fields.…”

Section: Introductionmentioning

confidence: 99%

Self-supervised blur detection from synthetically blurred scenes

Alvarez-Gila

Galdrán

Garrote

et al. 2019

Image and Vision Computing

View full text Add to dashboard Cite

Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of its blurred areas. Nevertheless, the effectiveness of such deep models is limited due to the scarcity of datasets annotated in terms of blur segmentation, as blur annotation is labour intensive. In this work, we bypass the need for such annotated datasets for end-to-end learning, and instead rely on object proposals and a model for blur generation in order to produce a dataset of synthetically blurred images. This allows us to perform self-supervised learning over the generated image and ground truth blur mask pairs using CNNs, defining a framework that can be employed in purely self-supervised, weakly supervised or semi-supervised configurations. Interestingly, experimental results of such setups over the largest blur segmentation datasets available show that this approach achieves state of the art results in blur segmentation, even without ever observing any real blurred image.

show abstract

A Unified Approach of Multi-scale Deep and Hand-Crafted Features for Defocus Estimation

Cited by 110 publications

References 39 publications

Synthetic defocus and look-ahead autofocus for casual videography

Synthetic defocus and look-ahead autofocus for casual videography

Image Sharpening With Blur Map Estimation Using Convolutional Neural Network

Self-supervised blur detection from synthetically blurred scenes

Contact Info

Product

Resources

About