1 code implementation • 13 Jun 2023 • Guangan Chen, Hanhe Lin, Oliver Wiedemann, Dietmar Saupe
By applying this framework, we created a novel PJND dataset, KonJND++, consisting of 300 source images, compressed versions thereof under JPEG or BPG compression, and an average of 43 ratings of PJND and 129 self-reported locations of JND-critical regions for each source image.
no code implementations • 29 Apr 2023 • Mohsen Jenadeleh, Johannes Zagermann, Harald Reiterer, Ulf-Dietrich Reips, Raouf Hamzaoui, Dietmar Saupe
The experimental results show that the inclusion of the ``not sure'' response option in the forced choice method reduced mental load and led to models with better data fit and correspondence to ground truth.
no code implementations • 12 Dec 2022 • Oliver Wiedemann, Vlad Hosu, Shaolin Su, Dietmar Saupe
Through KonX, we provide empirical evidence of label shifts caused by changes in the presentation resolution.
no code implementations • 11 Jul 2022 • Shaolin Su, Hanhe Lin, Vlad Hosu, Oliver Wiedemann, Jinqiu Sun, Yu Zhu, Hantao Liu, Yanning Zhang, Dietmar Saupe
An accurate computational model for image quality assessment (IQA) benefits many vision applications, such as image filtering, image processing, and image generation.
1 code implementation • 7 Oct 2021 • Jianxun Lou, Hanhe Lin, David Marshall, Dietmar Saupe, Hantao Liu
Due to the inherent inductive biases of CNN architectures, there is a lack of sufficient long-range contextual encoding capacity.
Ranked #1 on Saliency Prediction on SALICON
no code implementations • 31 Jul 2021 • Hui Men, Hanhe Lin, Mohsen Jenadeleh, Dietmar Saupe
We also provide the details for Thurstonian scale reconstruction from TC and our annotated dataset, KonFiG-IQA, containing 10 source images, processed using 7 distortion types at 12 or even 30 levels, uniformly spaced over a span of 3 JND units.
1 code implementation • 10 Sep 2020 • Franz Götz-Hahn, Vlad Hosu, Dietmar Saupe
Data used to train supervised machine learning models are commonly split into independent training, validation, and test sets.
no code implementations • 9 May 2020 • Franz Götz-Hahn, Vlad Hosu, Dietmar Saupe
In Neural Processing Letters 50, 3 (2019) a machine learning approach to blind video quality assessment was proposed.
1 code implementation • 20 Jan 2020 • Hanhe Lin, Vlad Hosu, Dietmar Saupe
We propose a new IQA dataset and a weakly supervised feature learning approach to train features more suitable for IQA of artificially distorted images.
no code implementations • 10 Jan 2020 • Hui Men, Vlad Hosu, Hanhe Lin, Andrés Bruhn, Dietmar Saupe
This re-ranking not only shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks, the results also provide the ground truth for designing novel image quality assessment (IQA) methods dedicated to perceptual quality of interpolated images.
1 code implementation • 7 Jan 2020 • Hanhe Lin, Vlad Hosu, Chunling Fan, Yun Zhang, Yuchen Mu, Raouf Hamzaoui, Dietmar Saupe
We then use deep feature learning to predict samples of the SUR curve and apply the method of least squares to fit the parametric model to the predicted samples.
no code implementations • 17 Dec 2019 • Franz Götz-Hahn, Vlad Hosu, Hanhe Lin, Dietmar Saupe
Video quality assessment (VQA) methods focus on particular degradation types, usually artificially induced on a small set of reference videos.
2 code implementations • 14 Oct 2019 • Vlad Hosu, Hanhe Lin, Tamas Sziranyi, Dietmar Saupe
Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets.
Ranked #16 on Video Quality Assessment on MSU NR VQA Database
no code implementations • 19 Aug 2019 • Markus Wagner, Hanhe Lin, Shujun Li, Dietmar Saupe
We compared 8 state-of-the-art algorithms for blind IQA and showed that an oracle, able to predict the best performing method for any given input image, yields a hybrid method that could outperform even the best single existing method by a large margin.
1 code implementation • CVPR 2019 • Vlad Hosu, Bastian Goldlucke, Dietmar Saupe
We propose an effective deep learning approach to aesthetics quality assessment that relies on a new type of pre-trained features, and apply it to the AVA data set, the currently largest aesthetics database.
Ranked #3 on Aesthetics Quality Assessment on AVA
no code implementations • 16 Jan 2019 • Hui Men, Hanhe Lin, Vlad Hosu, Daniel Maurer, Andres Bruhn, Dietmar Saupe
visual quality of interpolated frames mostly based on optical flow estimation.
1 code implementation • 22 Mar 2018 • Hanhe Lin, Vlad Hosu, Dietmar Saupe
The main challenge in applying state-of-the-art deep learning methods to predict image quality in-the-wild is the relatively small size of existing quality scored datasets.
Ranked #3 on Image Quality Assessment on KonIQ-10k