Two-Step Color-Polarization Demosaicking Network

• URL: http://arxiv.org/abs/2209.06027v1
• Date: Tue, 13 Sep 2022 14:28:18 GMT
• Title: Two-Step Color-Polarization Demosaicking Network
• Authors: Vy Nguyen, Masayuki Tanaka, Yusuke Monno, Masatoshi Okutomi
• Abstract summary: TCPDNet is a two-step color-polarization demosaicking network. TCPDNet outperforms existing methods in terms of the image quality of polarization images and the accuracy of Stokes parameters.
• Score: 14.5106375775521
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Polarization information of light in a scene is valuable for various image processing and computer vision tasks. A division-of-focal-plane polarimeter is a promising approach to capture the polarization images of different orientations in one shot, while it requires color-polarization demosaicking. In this paper, we propose a two-step color-polarization demosaicking network~(TCPDNet), which consists of two sub-tasks of color demosaicking and polarization demosaicking. We also introduce a reconstruction loss in the YCbCr color space to improve the performance of TCPDNet. Experimental comparisons demonstrate that TCPDNet outperforms existing methods in terms of the image quality of polarization images and the accuracy of Stokes parameters.

Related papers

• A Nerf-Based Color Consistency Method for Remote Sensing Images [0.5735035463793009]
  We propose a NeRF-based method of color consistency for multi-view images, which weaves image features together using implicit expressions, and then re-illuminates feature space to generate a fusion image with a new perspective. Experimental results show that the synthesize image generated by our method has excellent visual effect and smooth color transition at the edges.
  arXiv  Detail & Related papers  (2024-11-08T13:26:07Z)
• Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1 [51.404644401997736]
  We propose a complete framework to remove speckle in polarimetric SAR images using a convolutional neural network. Experiments show that the proposed approach offers exceptional results in both speckle reduction and resolution preservation.
  arXiv  Detail & Related papers  (2024-08-28T10:07:17Z)
• You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement [50.37253008333166]
  Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. We propose a novel trainable color space, named Horizontal/Vertical-Intensity (HVI) It not only decouples brightness and color from RGB channels to mitigate the instability during enhancement but also adapts to low-light images in different illumination ranges due to the trainable parameters.
  arXiv  Detail & Related papers  (2024-02-08T16:47:43Z)
• Polarized Color Image Denoising using Pocoformer [42.171036556122644]
  Polarized color photography provides both visual textures and object surficial information in one snapshot. The use of the directional polarizing filter array causes extremely lower photon count and SNR compared to conventional color imaging. We propose a learning-based approach to simultaneously restore clean signals and precise polarization information.
  arXiv  Detail & Related papers  (2022-07-01T05:52:14Z)
• Deep Polarization Imaging for 3D shape and SVBRDF Acquisition [7.86578678811226]
  We present a novel method for efficient acquisition of shape and spatially varying reflectance of 3D objects using polarization cues. Unlike previous works that have exploited polarization to estimate material or object appearance under certain constraints, we lift such restrictions by coupling polarization imaging with deep learning. We demonstrate our approach to achieve superior results compared to recent works employing deep learning in conjunction with flash illumination.
  arXiv  Detail & Related papers  (2021-05-06T17:58:43Z)
• Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding [88.46682991985907]
  We present an underwater image enhancement network via medium transmission-guided multi-color space embedding, called Ucolor. Our network can effectively improve the visual quality of underwater images by exploiting multiple color spaces embedding.
  arXiv  Detail & Related papers  (2021-04-27T07:35:30Z)
• Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo [61.6260594326246]
  We introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. Using separable 4D convolutions and 2D heat-maps reduces the size and makes more efficient.
  arXiv  Detail & Related papers  (2021-03-22T18:06:58Z)
• Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement [52.49231695707198]
  We investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps. Inspired by the color image formulation, we first estimate the degradation from low-light inputs to simulate the distortion of environment illumination color, and then refine the content to recover the loss of diffuse illumination color. Our proposed method has surpassed the SOTA by 0.95dB in PSNR on LOL1000 dataset and 3.18% in mAP on ExDark dataset.
  arXiv  Detail & Related papers  (2021-03-19T04:00:27Z)
• Monochrome and Color Polarization Demosaicking Using Edge-Aware Residual Interpolation [14.5106375775521]
  A microgrid image polarimeter enables us to acquire a set of polarization images in one shot. Since the polarimeter consists of an image sensor equipped with a monochrome or color polarization filter array, the demosaicking process to interpolate missing pixel values plays a crucial role in obtaining high-quality polarization images. We propose a novel MPFA demosaicking method based on edge-aware residual (EARI) and also extend it to CPFA demosaicking.
  arXiv  Detail & Related papers  (2020-07-28T15:04:36Z)
• Probabilistic Color Constancy [88.85103410035929]
  We define a framework for estimating the illumination of a scene by weighting the contribution of different image regions. The proposed method achieves competitive performance, compared to the state-of-the-art, on INTEL-TAU dataset.
  arXiv  Detail & Related papers  (2020-05-06T11:03:05Z)
• An end-to-end CNN framework for polarimetric vision tasks based on polarization-parameter-constructing network [19.622145287600386]
  Pixel-wise operations between polarimetric images are important for processing polarization information. In this paper, a novel end-to-end CNN framework for polarization vision tasks is proposed. Taking faster R-CNN as task network, the experimental results show that compared with existing methods, the proposed framework achieves much higher mean-average-precision (mAP) in object detection task.
  arXiv  Detail & Related papers  (2020-04-19T01:33:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.