Deep Depth From Focus

Hazırbaş, Caner; Soyer, Sebastian Georg; Staab, Maximilian Christian; Leal-Taixé, Laura; Cremers, Daniel

doi:10.48550/arxiv.1704.01085

Cited by 4 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, dead zones can be overcome using several images with various in-focus planes. In a single snapshot context, this can be obtained with unconventional optics such as a plenoptic camera [32] or a lens with chromatic aberration [33,12], but both at the cost of image quality (low resolution or chromatic aberration).…”

Section: Related Workmentioning

confidence: 99%

“…Learning depth from defocus blur. The existence of common datasets for depth estimation [35,1,32], containing pairs of RGB images and corresponding depth maps, facilitates the creation of synthetic defocused images using real camera parameters. Hence, a deep learning approach can be used.…”

Section: Related Workmentioning

confidence: 99%

“…However, the final network is used to conduct depth estimation from all-in-focus images. Hazirbas et al [32] propose to conduct depth estimation using a focal stack, which is more related to depth from focus approaches than DFD. Finally, [37] presents a network for depth estimation and deblurring using a single defocused image.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Deep Depth from Defocus: How Can Defocus Blur Improve 3D Estimation Using Dense Neural Networks?

Carvalho

Saux

Trouvé-Peloux

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Depth estimation is of critical interest for scene understanding and accurate 3D reconstruction. Most recent approaches in depth estimation with deep learning exploit geometrical structures of standard sharp images to predict corresponding depth maps. However, cameras can also produce images with defocus blur depending on the depth of the objects and camera settings. Hence, these features may represent an important hint for learning to predict depth. In this paper, we propose a full system for single-image depth prediction in the wild using depth-fromdefocus and neural networks. We carry out thorough experiments to test deep convolutional networks on real and simulated defocused images using a realistic model of blur variation with respect to depth. We also investigate the influence of blur on depth prediction observing model uncertainty with a Bayesian neural network approach. From these studies, we show that out-of-focus blur greatly improves the depth-prediction network performances. Furthermore, we transfer the ability learned on a synthetic, indoor dataset to real, indoor and outdoor images. For this purpose, we present a new dataset containing real all-focus and defocused images from a Digital Single-Lens Reflex (DSLR) camera, paired with ground truth depth maps obtained with an active 3D sensor for indoor scenes. The proposed approach is successfully validated on both this new dataset and standard ones as NYUv2 or Depth-in-the-Wild. Code and new datasets are available at https:// github.com/ marcelampc/ d3net depth estimation.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Depth from Defocus: How Can Defocus Blur Improve 3D Estimation Using Dense Neural Networks?

Carvalho

Saux

Trouvé-Peloux

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Since the lens response is depth dependent (due to different behaviour of in-and out-of-focus), this feature can be employed for depth estimation. Under this category one may find either depth from focus/defocus [Darrell and Wohn 1988;Schechner and Kiryati 2000;Trouvé et al 2013;Suwajanakorn et al 2015;Carvalho et al 2018;Gur and Wolf 2019], and depth from a focal stack [Lin et al 2013;Lin et al 2015;Hazirbas et al 2018]. A recent work [Guo et al 2017] attempts to combine two focal stacks (acquired using a light-field stereo pair) to achieve improved depth estimation.…”

Section: Monocular Depth Estimationmentioning

confidence: 99%

MonSter: Awakening the Mono in Stereo

Gil,

Elmalem,

Haim

et al. 2019

Preprint

View full text Add to dashboard Cite

It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in , https: //doi.org/10.1145/nnnnnnn.nnnnnnn. camera. The combination of these depth maps leads to more accurate depth estimation. Moreover, enforcing consistency between the extracted maps leads to a novel online self-calibration strategy. We present a prototype camera that demonstrates the benefits of the proposed combination, for both self-calibration and depth reconstruction in real-world scenes.

show abstract

“…Such overloading of terminology can create lasting confusion. New machine learning papers referring to deconvolution might be (i) invoking its original meaning, (ii) describing upconvolution, or (iii) attempting to resolve the confusion, as in [28], which awkwardly refers to "upconvolution (deconvolution)".…”

Section: Overloading Technical Terminologymentioning

confidence: 99%

Troubling Trends in Machine Learning Scholarship

Steinhardt¹

2018

Preprint

View full text Add to dashboard Cite

Deep Depth From Focus

Cited by 4 publications

References 0 publications

Deep Depth from Defocus: How Can Defocus Blur Improve 3D Estimation Using Dense Neural Networks?

Deep Depth from Defocus: How Can Defocus Blur Improve 3D Estimation Using Dense Neural Networks?

MonSter: Awakening the Mono in Stereo

Troubling Trends in Machine Learning Scholarship

Contact Info

Product

Resources

About