Waterloo Exploration Database: New Challenges for Image Quality Assessment Models

By Kede Ma, Zhengfang Duanmu, Q. Wu, Zhou Wang, Hongwei Yong, Hongliang Li, Lei Zhang. 2017

827 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “In our new degradation model, the JPEG quality factor is uniformly chosen from [30, 95].”
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild (2020, methodology): “To build the playground for gMAD, we combine all synthetically distorted images in the Waterloo Exploration Database [48] with a corpus of realistically distorted images from SPAQ [49].”
Learning Deep CNN Denoiser Prior for Image Restoration (2017, methodology): “Hence, instead of training on a small dataset consisting of 400 Berkeley segmentation dataset (BSD) images of size 180×180 [13], we collect a large dataset which includes 400 BSD images, 400 selected images from validation set of ImageNet database [20] and 4,744 images of Waterloo Exploration Databa”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, methodology): “We pre-train DA-IQA on Waterloo Exploration [39] and perform cross validation on TID2013 [40] and LIVE [41].”
Image denoising using deep CNN with batch renormalization (2020, methodology): “For Gaussian image denoising, we used 3,859 images from the Waterloo Exploration Database to train the model.”
PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference (2018, methodology): “Reference images: The proposed dataset contains 200 unique reference images (160 reference images are used for training and 40 for testing), which are selected from the Waterloo Exploration Database [36,37] because of its highquality images.”
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, methodology): “Dataset and test them on the large scale synthetic database Waterloo Exploration Database [25].”
A Deep Journey into Super-resolution (2019, methodology): “Training is performed on 5,944 images from BSD [49], DIV2K [50] and Waterloo [78] datasets.”
Variational Denoising Network: Toward Blind Noise Modeling and Removal (2019, methodology): “[45], we collected a set of source images to train the network, including 432 images from BSD [5], 400 images from the validation set of ImageNet [12] and 4744 images from the Waterloo Exploration Database [26].”
Blind Quality Assessment Based on Pseudo-Reference Image (2018, methodology): “Specifically, we select 100 high quality natural images from a public database [48], and generate the distorted images using the 4 most common”
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, methodology): “THE D-TEST, L-TEST AND P-TEST RESULTS ON THE EXPLORATION DATABASE [20], USING LISTNET [21] FOR TRAINING”
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising (2017, methodology): “We collected a large dataset of source images, including 400 BSD images, 400 images selected from the validation set of ImageNet [53], and the 4,744 images from the Waterloo Exploration Database [54].”
Image Restoration with Mean-Reverting Stochastic Differential Equations (2023, methodology): “To evaluate the image denoising performance, we train our models on 8 294 high-quality images collected from the DIV2K (Agustsson & Timofte, 2017), Flickr2K (Timofte et al., 2017), BSD500 (Arbelaez et al., 2010), and Waterloo Exploration datasets (Ma et al., 2016).”
Deep Learning for Image Super-Resolution: A Survey (2019, methodology): “ory keywords. Besides these datasets, some datasets widely used for other vision tasks are also employed in this ﬁeld, including ImageNet [53], MS-COCO [54], VOC2012 [55], CelebA [56], LSUN [57], WED [58], etc. In addition, combining multiple datasets for training is also popular, such as combining ”
Attention-guided CNN for image denoising (2020, methodology): “Training datasets We use 400 images with size of 180 × 180 from the Berkeley Segmentation Dataset (BSD) [36] and 3,859 images from the waterloo exploration database [31] to train the Gaussian synthetic denoising model.”
Residual Non-local Attention Networks for Image Restoration (2019, methodology): “Wang et al. (2017) proposed residual attention network for image classiﬁcation with a trunk-and-mask attention mechanism.”
End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, methodology): “The other three tests are introduced by Ma et al. [29] to account for largescale image databases without MOSs, such as the Waterloo Exploration Database [29] used in the paper.”
Multi-level Wavelet-CNN for Image Restoration (2018, background): “To train our MWCNN, a large training set is constructed by using images from three dataset, i.e. Berkeley Segmentation Dataset (BSD) [38], DIV2K [3] and Waterloo Exploration Database (WED) [35].”