690 citations · 1.5k across the 15 of their papers we have counts for
19 papers
AIM 2025 Challenge on Real-World RAW Image Denoising
Feiran Li, Jiacheng Li, Marcos V. Conde +4
We introduce the AIM 2025 Real-World RAW Image Denoising Challenge, aiming to advance efficient and effective denoising techniques grounded in data synthesis. The competition is bu…
Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution
Vlad Hosu, Lorenzo Agnolucci, Daisuke Iso +1
Image Quality Assessment (IQA) measures and predicts perceived image quality by human observers. Although recent studies have highlighted the critical influence that variations in…
AIM 2024 Challenge on UHD Blind Photo Quality Assessment
Vlad Hosu, Marcos V. Conde, Lorenzo Agnolucci +3
We introduce the AIM 2024 UHD-IQA Challenge, a competition to advance the No-Reference Image Quality Assessment (NR-IQA) task for modern, high-resolution photos. The challenge is b…
UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment
Vlad Hosu, Lorenzo Agnolucci, Oliver Wiedemann +2
We introduce a novel Image Quality Assessment (IQA) dataset comprising 6073 UHD-1 (4K) images, annotated at a fixed width of 3840 pixels. Contrary to existing No-Reference (NR) IQA…
KonX: Cross-Resolution Image Quality Assessment
Oliver Wiedemann, Vlad Hosu, Shaolin Su +1
Scale-invariance is an open problem in many computer vision subfields. For example, object labels should remain constant across scales, yet model predictions diverge in many cases.…
Fairness in generative modeling
Mariia Zameshina, Olivier Teytaud, Fabien Teytaud +4
We design general-purpose algorithms for addressing fairness issues and mode collapse in generative modeling. More precisely, to design fair algorithms for as many sensitive variab…
Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model
Shaolin Su, Hanhe Lin, Vlad Hosu +6
An accurate computational model for image quality assessment (IQA) benefits many vision applications, such as image filtering, image processing, and image generation. Although the…
EvolGAN: Evolutionary Generative Adversarial Networks
Baptiste Roziere, Fabien Teytaud, Vlad Hosu +4
We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both. The new…
Tarsier: Evolving Noise Injection in Super-Resolution GANs
Baptiste Roziere, Nathanal Carraz Rakotonirina, Vlad Hosu +4
Super-resolution aims at increasing the resolution and level of detail within an image. The current state of the art in general single-image super-resolution is held by NESRGAN+, w…
Critical analysis on the reproducibility of visual quality assessment using deep features
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. This paper illustrates that complex data leakage case…
Comment on "No-Reference Video Quality Assessment Based on the Temporal Pooling of Deep Features"
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. It is based on temporal pooling of features of video frames, ta…
DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning
Hanhe Lin, Vlad Hosu, Dietmar Saupe
Multi-level deep-features have been driving state-of-the-art methods for aesthetics and image quality assessment (IQA). However, most IQA benchmarks are comprised of artificially d…
Subjective Annotation for a Frame Interpolation Benchmark using Artefact Amplification
Hui Men, Vlad Hosu, Hanhe Lin +2
Current benchmarks for optical flow algorithms evaluate the estimation either directly by comparing the predicted flow fields with the ground truth or indirectly by using the predi…
SUR-FeatNet: Predicting the Satisfied User Ratio Curvefor Image Compression with Deep Feature Learning
Hanhe Lin, Vlad Hosu, Chunling Fan +4
The satisfied user ratio (SUR) curve for a lossy image compression scheme, e.g., JPEG, characterizes the complementary cumulative distribution function of the just noticeable diffe…
KonVid-150k: A Dataset for No-Reference Video Quality Assessment of Videos in-the-Wild
Franz Götz-Hahn, Vlad Hosu, Hanhe Lin +1
Video quality assessment (VQA) methods focus on particular degradation types, usually artificially induced on a small set of reference videos. Hence, most traditional VQA methods u…
KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment
Vlad Hosu, Hanhe Lin, Tamas Sziranyi +1
Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generatin…
Effective Aesthetics Prediction with Multi-level Spatially Pooled Features
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 l…
Technical Report on Visual Quality Assessment for Frame Interpolation
Hui Men, Hanhe Lin, Vlad Hosu +3
Current benchmarks for optical flow algorithms evaluate the estimation quality by comparing their predicted flow field with the ground truth, and additionally may compare interpola…
KonIQ-10k: Towards an ecologically valid and large-scale IQA database
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. The rea…