Luminance Attentive Networks for HDR Image and Panorama Reconstruction

• URL: http://arxiv.org/abs/2109.06688v1
• Date: Tue, 14 Sep 2021 13:44:34 GMT
• Title: Luminance Attentive Networks for HDR Image and Panorama Reconstruction
• Authors: Hanning Yu, Wentao Liu, Chengjiang Long, Bo Dong, Qin Zou, Chunxia Xiao
• Abstract summary: It is difficult to reconstruct a high inverse range from a low dynamic range (LDR) image as an ill-posed problem. This paper proposes a attentive luminance network named LANet for HDR reconstruction from a single LDR image.
• Score: 37.364335148790005
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: It is very challenging to reconstruct a high dynamic range (HDR) from a low dynamic range (LDR) image as an ill-posed problem. This paper proposes a luminance attentive network named LANet for HDR reconstruction from a single LDR image. Our method is based on two fundamental observations: (1) HDR images stored in relative luminance are scale-invariant, which means the HDR images will hold the same information when multiplied by any positive real number. Based on this observation, we propose a novel normalization method called " HDR calibration " for HDR images stored in relative luminance, calibrating HDR images into a similar luminance scale according to the LDR images. (2) The main difference between HDR images and LDR images is in under-/over-exposed areas, especially those highlighted. Following this observation, we propose a luminance attention module with a two-stream structure for LANet to pay more attention to the under-/over-exposed areas. In addition, we propose an extended network called panoLANet for HDR panorama reconstruction from an LDR panorama and build a dualnet structure for panoLANet to solve the distortion problem caused by the equirectangular panorama. Extensive experiments show that our proposed approach LANet can reconstruct visually convincing HDR images and demonstrate its superiority over state-of-the-art approaches in terms of all metrics in inverse tone mapping. The image-based lighting application with our proposed panoLANet also demonstrates that our method can simulate natural scene lighting using only LDR panorama. Our source code is available at https://github.com/LWT3437/LANet.

Related papers

• Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images [82.1477261107279]
  We propose the irradiance fields from sparse LDR panoramic images to increase the observation counts for faithful geometry recovery. Experiments demonstrate that the irradiance fields outperform state-of-the-art methods on both geometry recovery and HDR reconstruction.
  arXiv  Detail & Related papers  (2023-12-26T08:10:22Z)
• GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild [74.52723408793648]
  We present the first method for learning a generative model of HDR images from in-the-wild LDR image collections in a fully unsupervised manner. The key idea is to train a generative adversarial network (GAN) to generate HDR images which, when projected to LDR under various exposures, are indistinguishable from real LDR images. Experiments show that our method GlowGAN can synthesize photorealistic HDR images in many challenging cases such as landscapes, lightning, or windows.
  arXiv  Detail & Related papers  (2022-11-22T15:42:08Z)
• StyleLight: HDR Panorama Generation for Lighting Estimation and Editing [98.20167223076756]
  We present a new lighting estimation and editing framework to generate high-dynamic-range (GAN) indoor panorama lighting from a single field-of-view (LFOV) image. Our framework achieves superior performance over state-of-the-art methods on indoor lighting estimation.
  arXiv  Detail & Related papers  (2022-07-29T17:58:58Z)
• HDR-NeRF: High Dynamic Range Neural Radiance Fields [70.80920996881113]
  We present High Dynamic Range Neural Radiance Fields (-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. We are able to generate both novel HDR views and novel LDR views under different exposures.
  arXiv  Detail & Related papers  (2021-11-29T11:06:39Z)
• HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN [24.299931323012757]
  Low Dynamic Range (LDR) cameras are incapable of representing the wide dynamic range of the real-world scene. We propose a deep learning based approach to recover details in the saturated areas while reconstructing the HDR image. We present a novel conditional GAN (cGAN) based framework trained in an end-to-end fashion over the HDR-REAL and HDR-SYNTH datasets.
  arXiv  Detail & Related papers  (2021-10-04T18:50:35Z)
• A Two-stage Deep Network for High Dynamic Range Image Reconstruction [0.883717274344425]
  This study tackles the challenges of single-shot LDR to HDR mapping by proposing a novel two-stage deep network. Notably, our proposed method aims to reconstruct an HDR image without knowing hardware information, including camera response function (CRF) and exposure settings.
  arXiv  Detail & Related papers  (2021-04-19T15:19:17Z)
• Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas [60.24132321381606]
  We introduce the physical illuminance constraints to our single-shot HDR reconstruction framework. Our method can generate HDRs which are not only visually appealing but also physically plausible.
  arXiv  Detail & Related papers  (2021-03-24T01:51:19Z)
• Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array [14.5106375775521]
  We introduce the idea of luminance normalization that simultaneously enables effective loss and input data normalization. Experimental results using two public HDR image datasets demonstrate that our framework outperforms other snapshot methods.
  arXiv  Detail & Related papers  (2020-11-20T06:31:37Z)
• HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions [62.44802076971331]
  We propose a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content.
  arXiv  Detail & Related papers  (2020-07-03T11:42:35Z)

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.