Hierarchical Regression Network for Spectral Reconstruction from RGB Images

• URL: http://arxiv.org/abs/2005.04703v1
• Date: Sun, 10 May 2020 16:06:11 GMT
• Title: Hierarchical Regression Network for Spectral Reconstruction from RGB Images
• Authors: Yuzhi Zhao, Lai-Man Po, Qiong Yan, Wei Liu, Tingyu Lin
• Abstract summary: We propose a 4-level Hierarchical Regression Network (HRNet) with PixelShuffle layer as inter-level interaction. We evaluate proposed HRNet with other architectures and techniques by participating in NTIRE 2020 Challenge on Spectral Reconstruction from RGB Images.
• Score: 21.551899202524904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Capturing visual image with a hyperspectral camera has been successfully applied to many areas due to its narrow-band imaging technology. Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by discovering an inverse response function. Current works mainly map RGB images directly to corresponding spectrum but do not consider context information explicitly. Moreover, the use of encoder-decoder pair in current algorithms leads to loss of information. To address these problems, we propose a 4-level Hierarchical Regression Network (HRNet) with PixelShuffle layer as inter-level interaction. Furthermore, we adopt a residual dense block to remove artifacts of real world RGB images and a residual global block to build attention mechanism for enlarging perceptive field. We evaluate proposed HRNet with other architectures and techniques by participating in NTIRE 2020 Challenge on Spectral Reconstruction from RGB Images. The HRNet is the winning method of track 2 - real world images and ranks 3rd on track 1 - clean images. Please visit the project web page https://github.com/zhaoyuzhi/Hierarchical-Regression-Network-for-Spectral-Reconstruction-from-RGB-Im ages to try our codes and pre-trained models.

Related papers

• Rethinking RGB Color Representation for Image Restoration Models [55.81013540537963]
  We augment the representation to hold structural information of local neighborhoods at each pixel. Substituting the underlying representation space for the per-pixel losses facilitates the training of image restoration models. Our space consistently improves overall metrics by reconstructing both color and local structures.
  arXiv  Detail & Related papers  (2024-02-05T06:38:39Z)
• DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation [76.81628995237058]
  DFormer is a novel framework to learn transferable representations for RGB-D segmentation tasks. It pretrains the backbone using image-depth pairs from ImageNet-1K. DFormer achieves new state-of-the-art performance on two popular RGB-D tasks.
  arXiv  Detail & Related papers  (2023-09-18T11:09:11Z)
• Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution [52.582632746409665]
  We propose a novel Symmetric Uncertainty-aware Feature Transmission (SUFT) for color-guided DSR. Our method achieves superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-01T06:35:59Z)
• Learning to Recover Spectral Reflectance from RGB Images [20.260831758913902]
  spectral reflectance recovery (SRR) from RGB images is challenging and costly. Most existing approaches are trained on synthetic images and utilize the same parameters for all unseen testing images. We propose a self-supervised meta-auxiliary learning (MAXL) strategy that fine-tunes the well-trained network parameters with each testing image to combine external with internal information.
  arXiv  Detail & Related papers  (2023-04-04T23:27:02Z)
• Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution [123.04455334124188]
  Guided depth map super-resolution (GDSR) aims to upsample low-resolution (LR) depth maps with additional information involved in high-resolution (HR) RGB images from the same scene. In this paper, we propose the Spherical Space feature Decomposition Network (SSDNet) to solve the above issues. Our method can achieve state-of-the-art results on four test datasets, as well as successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2023-03-15T21:22:21Z)
• RGB-D Image Inpainting Using Generative Adversarial Network with a Late Fusion Approach [14.06830052027649]
  Diminished reality is a technology that aims to remove objects from video images and fills in the missing region with plausible pixels. We propose an RGB-D image inpainting method using generative adversarial network.
  arXiv  Detail & Related papers  (2021-10-14T14:44:01Z)
• Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild [48.44194221801609]
  We propose a new lightweight and end-to-end learning-based framework to tackle this challenge. We progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective camera spectral response function estimation. Our method significantly outperforms state-of-the-art unsupervised methods and even exceeds the latest supervised method under some settings.
  arXiv  Detail & Related papers  (2021-08-15T05:19:44Z)
• Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images [42.26124628784883]
  We propose a compact, efficient, and end-to-end learning-based framework, namely AGD-Net. We first formulate the problem explicitly based on the classic gradient descent algorithm. AGD-Net can improve the reconstruction quality by more than 1.0 dB on average.
  arXiv  Detail & Related papers  (2021-08-12T05:54:09Z)
• Over-and-Under Complete Convolutional RNN for MRI Reconstruction [57.95363471940937]
  Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture. We propose an Over-and-Under Complete Convolu?tional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN) The proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.
  arXiv  Detail & Related papers  (2021-06-16T15:56:34Z)
• AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images [22.26917280683572]
  We propose a novel adaptive weighted attention network (AWAN) for spectral reconstruction. AWCA and PSNL modules are developed to reallocate channel-wise feature responses. In the NTIRE 2020 Spectral Reconstruction Challenge, our entries obtain the 1st ranking on the Clean track and the 3rd place on the Real World track.
  arXiv  Detail & Related papers  (2020-05-19T09:21:01Z)

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.