Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

• URL: http://arxiv.org/abs/2307.03998v2
• Date: Sat, 16 Dec 2023 09:17:13 GMT
• Title: Lightweight Improved Residual Network for Efficient Inverse Tone Mapping
• Authors: Liqi Xue, Tianyi Xu, Yongbao Song, Yan Liu, Lei Zhang, Xiantong Zhen, and Jun Xu
• Abstract summary: Most media images on the internet remain in 8-bit standard dynamic range (SDR) format. Inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. We propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM.
• Score: 30.049931061503276
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline.

Related papers

• CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task [44.14681936953848]
  Composite Refinement Network (CRNet) can perform unified image restoration and enhancement. CRNet explicitly separates and strengthens high and low-frequency information through pooling layers. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge.
  arXiv  Detail & Related papers  (2024-04-22T12:33:18Z)
• FastHDRNet: A new efficient method for SDR-to-HDR Translation [5.224011800476952]
  We propose a neural network for SDR to HDR conversion, termed "FastNet" The architecture is designed as a lightweight network that utilizes global statistics and local information with super high efficiency.
  arXiv  Detail & Related papers  (2024-04-06T03:25:24Z)
• Generating Content for HDR Deghosting from Frequency View [56.103761824603644]
  Recent Diffusion Models (DMs) have been introduced in HDR imaging field. DMs require extensive iterations with large models to estimate entire images. We propose the Low-Frequency aware Diffusion (LF-Diff) model for ghost-free HDR imaging.
  arXiv  Detail & Related papers  (2024-04-01T01:32:11Z)
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes [58.66427721308464]
  Self is a self-supervised reconstruction method that only requires dynamic multi-exposure images during training. Self achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones.
  arXiv  Detail & Related papers  (2023-10-03T07:10:49Z)
• Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation [51.26219245226384]
  Modern displays are capable of rendering video content with high dynamic range (WCG) and wide color gamut (SDR) The majority of available resources are still in standard dynamic range (SDR) We define and analyze the SDRTV-to-TV task by modeling the formation of SDRTV/TV content. Our method is primarily designed for ultra-high-definition TV content and is therefore effective and lightweight for processing 4K resolution images.
  arXiv  Detail & Related papers  (2023-09-08T02:50:54Z)
• Efficient HDR Reconstruction from Real-World Raw Images [16.54071503000866]
  High-definition screens on edge devices stimulate a strong demand for efficient high dynamic range ( HDR) algorithms. Many existing HDR methods either deliver unsatisfactory results or consume too much computational and memory resources. In this work, we discover an excellent opportunity for HDR reconstructing directly from raw images and investigating novel neural network structures.
  arXiv  Detail & Related papers  (2023-06-17T10:10:15Z)
• Invertible Tone Mapping with Selectable Styles [19.03179521805971]
  In this paper, we propose an invertible tone mapping method that converts the multi-exposure HDR to a true LDR. Our invertible LDR can mimic the appearance of a user-selected tone mapping style. It can be shared over any existing social network platforms that may re-encode or format-convert the uploaded images.
  arXiv  Detail & Related papers  (2021-10-09T07:32:36Z)
• Deep Burst Super-Resolution [165.90445859851448]
  We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
  arXiv  Detail & Related papers  (2021-01-26T18:57:21Z)
• Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS [63.48801313087118]
  We propose a new method for image superresolution using deep residual network with dense skip connections. The proposed method won the first place in all three tracks of the AIM 2020 Real Image Super-Resolution Challenge.
  arXiv  Detail & Related papers  (2020-09-02T22:33:23Z)
• DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution [69.2432352477966]
  Real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair.
  arXiv  Detail & Related papers  (2020-02-25T18:24:51Z)

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.