RankIQA: Learning from Rankings for No-Reference Image Quality Assessment

Liu, Xialei; Weijer, Joost van de; Bagdanov, Andrew D.

doi:10.1109/iccv.2017.118

Cited by 405 publications

(304 citation statements)

References 39 publications

Supporting

Mentioning

303

Contrasting

Order By: Relevance

“…• Ranking plus fine-tuning: In this approach the network is first trained on the large dataset of ranking data, and is next fine-tuned on the smaller dataset for which density maps are available. To the best of our knowledge this is the approach which is used by all self-supervised methods in vision [10,26,36,24,20].…”

Section: Combining Counting and Ranking Datamentioning

confidence: 99%

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Liu

Weijer

Bagdanov

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

279

222

View full text Add to dashboard Cite

We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking of cropped images , we use the observation that any sub-image of a crowded scene image is guaranteed to contain the same number or fewer persons than the super-image. This allows us to address the problem of limited size of existing datasets for crowd counting. We collect two crowd scene datasets from Google using keyword searches and queryby-example image retrieval, respectively. We demonstrate how to efficiently learn from these unlabeled datasets by incorporating learning-to-rank in a multi-task network which simultaneously ranks images and estimates crowd density maps. Experiments on two of the most challenging crowd counting datasets show that our approach obtains state-ofthe-art results.

show abstract

Section: Combining Counting and Ranking Datamentioning

confidence: 99%

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Liu

Weijer

Bagdanov

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

279

222

View full text Add to dashboard Cite

show abstract

“…However, HVS treats artifact signals unevenly according to areas of images. Artifacts lie in low frequency or edge areas are emphasized and ones lie in high frequency areas are tend to be masked, as demonstrated in the task of perceptual metrics learning [31,24,25,56]. Thus, we can draw a reasonable explanation for subpixel convolution on the improvements of perceptual measurements.…”

Section: Quality-aware Synthesismentioning

confidence: 83%

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

Qian

Lin

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

InputFace Manipulation Results of Our Model Figure 1: Face manipulation results on in-the-wild samples via transferring knowledge learned from the CelebA dataset. The first column shows input images and the remainders are images generated by AF-VAE with target expression/rotation boundary maps as the condition. Note that the model is fine-tuned with movie clip frames from YouTube of 256 × 256 resolution. All the generated poses are unseen before. AbstractRecent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to lowresolution and lack of diversity.In this work, we propose Additive Focal Variational Auto-encoder (AF-VAE), a novel approach that can arbitrarily manipulate high-resolution face images using a simple yet effective model and only weak supervision of reconstruction and KL divergence losses. First, a novel additive Gaussian Mixture assumption is introduced with an unsupervised clustering mechanism in the structural latent 1 Work done during an internship at SenseTime Research. space, which endows better disentanglement and boosts multi-modal representation with external memory. Second, to improve the perceptual quality of synthesized results, two simple strategies in architecture design are further tailored and discussed on the behavior of Human Visual System (HVS) for the first time, allowing for fine control over the model complexity and sample quality. Human opinion studies and new state-of-the-art Inception Score (IS) / Fréchet Inception Distance (FID) demonstrate the superiority of our approach over existing algorithms, advancing both the fidelity and extremity of face manipulation task.

show abstract

“…Instead of learning IQA scores directly, they fine tune the network to learn a probabilistic representation of distorted images. According to the distortion types and levels in particular datasets, Liu et al [25] synthesize masses of ranked images to train a Siamese network to learn the rankings for NR-IQA. Liang et al [24] propose to use non-aligned similar scene as a reference.…”

Section: Related Workmentioning

confidence: 99%

Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning

Lin

Wang²

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

207

104

View full text Add to dashboard Cite

No-reference image quality assessment (NR-IQA) is a fundamental yet challenging task in low-level computer vision community. The difficulty is particularly pronounced for the limited information, for which the corresponding reference for comparison is typically absent. Although various feature extraction mechanisms have been leveraged from natural scene statistics to deep neural networks in previous methods, the performance bottleneck still exists.In this work, we propose a hallucination-guided quality regression network to address the issue. We firstly generate a hallucinated reference constrained on the distorted image, to compensate the absence of the true reference. Then, we pair the information of hallucinated reference with the distorted image, and forward them to the regressor to learn the perceptual discrepancy with the guidance of an implicit ranking relationship within the generator, and therefore produce the precise quality prediction. To demonstrate the effectiveness of our approach, comprehensive experiments are evaluated on four popular image quality assessment benchmarks. Our method significantly outperforms all the previous state-of-the-art methods by large margins. The code and model are publicly available on the project page https://kwanyeelin.github. io/projects/HIQA/HIQA.html.

show abstract

RankIQA: Learning from Rankings for No-Reference Image Quality Assessment

Cited by 405 publications

References 39 publications

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning

Contact Info

Product

Resources

About