Blur-Aware Disparity Estimation from Defocus Stereo Images

Chen, Ching‐Hui; Zhong, Hui; Ahonen, Timo

doi:10.1109/iccv.2015.104

Cited by 24 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The network design of ASM is inspired by the best practices of defocus blur matching [9] and depth from narrowbaseline light-field image [24]. We design a network that captures blurry texture features to estimate the relative blur, and a dynamic sampling strategy for narrow-baseline stereo matching, as illustrated in Fig.…”

Section: Adaptive Sampling Modulementioning

confidence: 99%

See 1 more Smart Citation

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Kang¹,

Choe²,

Ha³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Adaptive Sampling Modulementioning

confidence: 99%

“…We design a self-3D attention given volumetric feature V to encode the amount of blur in texture features and aggregate the matching cost in homogeneous regions [9]. The layer consists of several 3D convolutional layers and the Sigmoid function.…”

Section: Adaptive Sampling Modulementioning

confidence: 99%

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Kang¹,

Choe²,

Ha³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This approximation is exact when the PSF is a Gaussian. Since the radius of the relative blur kernel σ r cannot indicate whether the (i) or the ( j) view is more in-focus than the other, we define the relative blur similarly to Chen et al (2015), as…”

Section: Relative Blur Calibration Using Bap Featuresmentioning

confidence: 99%

Leveraging blur information for plenoptic camera calibration

Labussière,

Teulière,

Bernardin

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents a novel calibration algorithm for plenoptic cameras, especially the multi-focus configuration, where several types of micro-lenses are used, using raw images only. Current calibration methods rely on simplified projection models, use features from reconstructed images, or require separated calibrations for each type of micro-lens. In the multi-focus configuration, the same part of a scene will demonstrate different amounts of blur according to the micro-lens focal length. Usually, only micro-images with the smallest amount of blur are used. In order to exploit all available data, we propose to explicitly model the defocus blur in a new camera model with the help of our newly introduced Blur Aware Plenoptic (BAP) feature. First, it is used in a pre-calibration step that retrieves initial camera parameters, and second, to express a new cost function to be minimized in our single optimization process. Third, it is exploited to calibrate the relative blur between micro-images. It links This work was supported by the AURA Region and the European Union (FEDER) through the MMII project of CPER 2015-2020 MMaSyF challenge.

show abstract

“…When the camera aperture is large such that the scene is no longer contained within the depth of field of the camera, focus blur is apparent in the captured images. There have been attempts to exploit this focus blur as an additional depth cue to compensate for the degraded stereo performance [6,34,7,13]. Furthermore, Takeda et al [33] proposed the addition of amplitude masks in the aperture plane.…”

Section: Related Workmentioning

confidence: 99%

CodedStereo: Learned Phase Masks for Large Depth-of-field Stereo

Tan

et al. 2021

Preprint

View full text Add to dashboard Cite

Conventional stereo suffers from a fundamental trade-off between imaging volume and signal-to-noise ratio (SNR)due to the conflicting impact of aperture size on both these variables. Inspired by the extended depth of field cameras, we propose a novel end-to-end learning-based technique to overcome this limitation, by introducing a phase mask at the aperture plane of the cameras in a stereo imaging system. The phase mask creates a depth-dependent yet numerically invertible point spread function, allowing us to recover sharp image texture and stereo correspondence over a significantly extended depth of field (EDOF) than conventional stereo. The phase mask pattern, the EDOF image reconstruction, and the stereo disparity estimation are all trained together using an end-to-end learned deep neural network. We perform theoretical analysis and characterization of the proposed approach and show a 6× increase in volume that can be imaged in simulation. We also build an experimental prototype and validate the approach using real-world results acquired using this prototype system.

show abstract

Blur-Aware Disparity Estimation from Defocus Stereo Images

Cited by 24 publications

References 25 publications

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

Leveraging blur information for plenoptic camera calibration

CodedStereo: Learned Phase Masks for Large Depth-of-field Stereo

Contact Info

Product

Resources

About