A fast and robust depth estimation method for 3D cameras

Shim, Seong-O; Choi, Tae‐Sun

doi:10.1109/icce.2012.6161887

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means the depth resolution is directly proportional to the number of images available. To augment the resolution, filters are applied to focus measure [26,36] or smooth surfaces are fitted to the estimated depths [39]. Depthfrom-defocus with a single image is also targeted by numerous methods [1,2,3,23,24,28,49] that used focus measures and filters.…”

Section: Input Imagementioning

confidence: 99%

Depth Estimation and Blur Removal from a Single Out-of-focus Image

Anwar¹,

Hayder²,

Porikli³

2017

Procedings of the British Machine Vision Conference 2017

View full text Add to dashboard Cite

This paper presents a depth estimation method that leverages rich representations learned from cascaded convolutional and fully connected neural networks operating on a patch-pooled set of feature maps. Our method is very fast and it substantially improves depth accuracy over the state-of-the-art alternatives, and from this, we computationally reconstruct an all-focus image and achieve synthetic re-focusing, all from a single image. Our experiments on benchmark datasets such as Make3D and NYU-v2 demonstrate superior performance in comparison to other available depth estimation methods by reducing the root-mean-squared error by 57% & 46%, and blur removal methods by 0.36 dB & 0.72 dB in PSNR, respectively. This improvement is also demonstrated by the superior performance using real defocus images.

show abstract