Deep Polarimetric HDR Reconstruction

Ting, Juiwen; Shakeri, Moein; Zhang, Hong

doi:10.48550/arxiv.2203.14190

Cited by 2 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The major drawback of these approaches is that real-world scenes rarely exhibit high DoLP, and this is required to correctly map a polarimetric image into an image with equivalent exposure time. To mitigate this issue, the authors proposed another technique, named DPHR [ 14 ]. In order to improve poorly exposed pixels with low DoLP, [ 14 ] generated HDR with a PFA camera by using the degree of polarization as the cue in a CNN (similar to U-Net [ 62 ]) to create a feature mask.…”

Section: Related Workmentioning

confidence: 99%

“…To mitigate this issue, the authors proposed another technique, named DPHR [ 14 ]. In order to improve poorly exposed pixels with low DoLP, [ 14 ] generated HDR with a PFA camera by using the degree of polarization as the cue in a CNN (similar to U-Net [ 62 ]) to create a feature mask. Image areas with high DoLP were reconstructed using a traditional approach (as in [ 3 ]), while pixels with moderate DoLP were reconstructed with both CNN and traditional techniques.…”

Section: Related Workmentioning

confidence: 99%

“…PFA cameras are also shown to be useful for HDR imaging [ 3 , 13 , 14 , 15 ]: these cameras can capture four images simultaneously with polarizers at different orientations. Since each linear polarizer reduces the observed intensity according to the degree of polarization of incoming light, the filter acts as an exposure time reduction and, thus, an equivalent exposure time can be computed to perform HDR reconstruction.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting Light Polarization for Deep HDR Imaging from a Single Exposure

Pistellato

Fatima

Wimmer

2023

Sensors

View full text Add to dashboard Cite

In computational photography, high dynamic range (HDR) imaging refers to the family of techniques used to recover a wider range of intensity values compared to the limited range provided by standard sensors. Classical techniques consist of acquiring a scene-varying exposure to compensate for saturated and underexposed regions, followed by a non-linear compression of intensity values called tone mapping. Recently, there has been a growing interest in estimating HDR images from a single exposure. Some methods exploit data-driven models trained to estimate values outside the camera’s visible intensity levels. Others make use of polarimetric cameras to reconstruct HDR information without exposure bracketing. In this paper, we present a novel HDR reconstruction method that employs a single PFA (polarimetric filter array) camera with an additional external polarizer to increase the scene’s dynamic range across the acquired channels and to mimic different exposures. Our contribution consists of a pipeline that effectively combines standard HDR algorithms based on bracketing and data-driven solutions designed to work with polarimetric images. In this regard, we present a novel CNN (convolutional neural network) model that exploits the underlying mosaiced pattern of the PFA in combination with the external polarizer to estimate the original scene properties, and a second model designed to further improve the final tone mapping step. The combination of such techniques enables us to take advantage of the light attenuation given by the filters while producing an accurate reconstruction. We present an extensive experimental section in which we validate the proposed method on both synthetic and real-world datasets specifically acquired for the task. Quantitative and qualitative results show the effectiveness of the approach when compared to state-of-the-art methods. In particular, our technique exhibits a PSNR (peak signal-to-noise ratio) on the whole test set equal to 23 dB, which is 18% better with respect to the second-best alternative.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting Light Polarization for Deep HDR Imaging from a Single Exposure

Pistellato

Fatima

Wimmer

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…On one hand, detecting the specular reflection can help us to infer the light direction, scene geometry [16] and camera location. On the other hand, the existence of specular reflection presents difficulties for many applications including image segmentation, object detection [11,25,26], pattern recognition [5], background subtraction [29,28,3], HDR reconstruction [44,37], tracking [7,27], and 3D reconstruction [24,18]. Therefore, the specular reflection from im- ages is a crucially important consideration in a variety of computer vision and robotics tasks.…”

Section: Introductionmentioning

confidence: 99%

Highlight Specular Reflection Separation based on Tensor Low-rank and Sparse Decomposition Using Polarimetric Cues

Shakeri¹,

Zhang²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper is concerned with specular reflection removal based on tensor low-rank decomposition framework with the help of polarization information. Our method is motivated by the observation that the specular highlight of an image is sparsely distributed while the remaining diffuse reflection can be well approximated by a linear combination of several distinct colors using a low-rank and sparse decomposition framework. Unlike current solutions, our tensor low-rank decomposition keeps the spatial structure of specular and diffuse information which enables us to recover the diffuse image under strong specular reflection or in saturated regions. We further define and impose a new polarization regularization term as constraint on color channels. This regularization boosts the performance of the method to recover an accurate diffuse image by handling the color distortion, a common problem of chromaticitybased methods, especially in case of strong specular reflection. Through comprehensive experiments on both synthetic and real polarization images, we demonstrate that our method is able to significantly improve the accuracy of highlight specular removal, and outperform the competitive methods to recover the diffuse image, especially in regions of strong specular reflection or in saturated areas.

show abstract

Deep Polarimetric HDR Reconstruction

Cited by 2 publications

References 40 publications

Exploiting Light Polarization for Deep HDR Imaging from a Single Exposure

Exploiting Light Polarization for Deep HDR Imaging from a Single Exposure

Highlight Specular Reflection Separation based on Tensor Low-rank and Sparse Decomposition Using Polarimetric Cues

Contact Info

Product

Resources

About