Benchmarking Ultra-High-Definition Image Reflection Removal

• URL: http://arxiv.org/abs/2308.00265v2
• Date: Fri, 08 Nov 2024 15:10:11 GMT
• Title: Benchmarking Ultra-High-Definition Image Reflection Removal
• Authors: Zhenyuan Zhang, Zhenbo Song, Kaihao Zhang, Zhaoxin Fan, Jianfeng Lu,
• Abstract summary: We propose a transformer-based architecture named RRFormer for reflection removal. We show that RRFormer achieves state-of-the-art performance on both the non-UHD dataset and our proposed UHDRR datasets.
• Score: 25.02234305857731
• License:
• Abstract: Deep learning based methods have achieved significant success in the task of single image reflection removal (SIRR). However, the majority of these methods are focused on High-Definition/Standard-Definition (HD/SD) images, while ignoring higher resolution images such as Ultra-High-Definition (UHD) images. With the increasing prevalence of UHD images captured by modern devices, in this paper, we aim to address the problem of UHD SIRR. Specifically, we first synthesize two large-scale UHD datasets, UHDRR4K and UHDRR8K. The UHDRR4K dataset consists of $2,999$ and $168$ quadruplets of images for training and testing respectively, and the UHDRR8K dataset contains $1,014$ and $105$ quadruplets. To the best of our knowledge, these two datasets are the first largest-scale UHD datasets for SIRR. Then, we conduct a comprehensive evaluation of six state-of-the-art SIRR methods using the proposed datasets. Based on the results, we provide detailed discussions regarding the strengths and limitations of these methods when applied to UHD images. Finally, we present a transformer-based architecture named RRFormer for reflection removal. RRFormer comprises three modules, namely the Prepossessing Embedding Module, Self-attention Feature Extraction Module, and Multi-scale Spatial Feature Extraction Module. These modules extract hypercolumn features, global and partial attention features, and multi-scale spatial features, respectively. To ensure effective training, we utilize three terms in our loss function: pixel loss, feature loss, and adversarial loss. We demonstrate through experimental results that RRFormer achieves state-of-the-art performance on both the non-UHD dataset and our proposed UHDRR datasets. The code and datasets are publicly available at https://github.com/Liar-zzy/Benchmarking-Ultra-High-Definition-Single-Image-Reflection-Removal.

Related papers

• Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation [53.95204595640208]
  Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. Previous approaches have generated synthetic images at high resolutions without leveraging information from real images. MUSE generates images at lower resolutions while using Class Activation Maps (CAMs) to ensure that the generated images retain critical, class-specific features.
  arXiv  Detail & Related papers  (2024-11-26T02:23:31Z)
• Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration [11.866565346920781]
  D2Net enables direct full-resolution inference on Ultra-high-definition (UHD) images. We show that our model achieves better quantitative and qualitative results than state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-10T13:05:36Z)
• A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Translation [0.0]
  Low Dynamic Range (LDR) to High Dynamic Range () image translation is an important computer vision problem. Most current state-of-the-art methods require high-quality paired LDR, datasets for model training. We propose a modified cycle-consistent adversarial architecture and utilize unpaired LDR, datasets for training.
  arXiv  Detail & Related papers  (2024-10-19T11:11:58Z)
• Rethinking Image Super-Resolution from Training Data Perspectives [54.28824316574355]
  We investigate the understudied effect of the training data used for image super-resolution (SR) With this, we propose an automated image evaluation pipeline. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance.
  arXiv  Detail & Related papers  (2024-09-01T16:25:04Z)
• Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency [51.36674160287799]
  We design a multi-branch deep neural network (DNN) to assess the quality of UHD images from three perspectives. aesthetic features are extracted from low-resolution images downsampled from the UHD ones. Technical distortions are measured using a fragment image composed of mini-patches cropped from UHD images. The salient content of UHD images is detected and cropped to extract quality-aware features from the salient regions.
  arXiv  Detail & Related papers  (2024-09-01T15:26:11Z)
• Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution [37.42524995828323]
  We construct UHD snow and rain benchmarks, named UHD-Snow and UHD-Rain. Each benchmark contains 3200 degraded/clear image pairs of 4K resolution. We propose an effective UHD image restoration solution by considering gradient and normal priors in model design.
  arXiv  Detail & Related papers  (2024-06-19T14:58:49Z)
• Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method [42.331058889312466]
  This paper contributes the first large-scale UHD image deraining dataset, 4K-Rain13k, that contains 13,000 image pairs at 4K resolution. We develop an effective and efficient vision-based architecture (UDR-Mixer) to better solve this task.
  arXiv  Detail & Related papers  (2024-05-27T11:45:08Z)
• Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement [78.67036949708795]
  Ultra-High-Definition (UHD) photo has gradually become the standard configuration in advanced imaging devices. We propose a new solution, UHDFour, that embeds Fourier transform into a cascaded network. We also contribute the first real UHD LLIE dataset, textbfUHD-LL, that contains 2,150 low-noise/normal-clear 4K image pairs.
  arXiv  Detail & Related papers  (2023-02-23T07:43:41Z)
• WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets for hyperspectral image classification [5.281167336437183]
  A new benchmark dataset named the Wuhan UAV-borne hyperspectral image (WHU-Hi) dataset was built for hyperspectral image classification. The WHU-Hi dataset has a high spectral resolution (nm level) and a very high spatial resolution (cm level) Some start-of-art hyperspectral image classification methods benchmarked the WHU-Hi dataset, and the experimental results show that WHU-Hi is a challenging dataset.
  arXiv  Detail & Related papers  (2020-12-27T11:28:37Z)
• 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.