AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment
Open accessThe DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index.
Abstract
With the rapid advancements of the text-to-image generative model, AI-generated images (AGIs) have been widely applied to entertainment, education, social media, etc. However, considering the large quality variance among different AGIs, there is an urgent need for quality models that are consistent with human subjective ratings. To address this issue, we extensively consider various popular AGI models, generated AGI through different prompts and model parameters, and collected subjective scores at the perceptual quality and text-to-image alignment, thus building the most comprehensive AGI subjective quality database AGIQA-3K so far. Furthermore, we conduct a benchmark experiment on this database to evaluate the consistency between the current Image Quality Assessment (IQA) model and human perception, while proposing StairReward that significantly improves the assessment performance of subjective text-to-image alignment. We believe that the fine-grained subjective scores in AGIQA-3K will inspire subsequent AGI quality models to fit human subjective perception mechanisms at both perception and alignment levels and to optimize the generation result of future AGI models. The database is released on https://github.com/lcysyzxdxc/AGIQA-3k-Database.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The Adam optimizer [64] (with an initial learning rate of 0.”
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 2×
“For SVR models, the repeating time is 1,000, implemented by LIBSVM [62] with radial basis function (RBF) kernel.”
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302 · cited 4×
“To analyze the assessment consistency of the perception model and subjective score generated by different T2I AGI models, we divide six AGI models into three groups, namely bad model (AttnGAN [6], GLIDE [10]), medium model (DALLE2 [33], Stable Diffusion [11]), and good model (Midjourney [34], Stable Diffusion XL) base…”
BackgroundMethodInfluentialGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Making a “Completely Blind” Image Quality Analyzer
Mittal, A., Soundararajan, R., & Bovik, A. C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2227726 · Cited by 6,766 · cited 2×
“II-A reviewed: ● Handcrafted-based models: This group includes four mainstream perceptual quality metrics, namely CEIQ [51], DSIQA [52], NIQE [53], and Sisblim [43].”
MethodStackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.629 · Cited by 3,021
A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
Sheikh, H. R., Sabir, M. F., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881959 · Cited by 2,966 · cited 1×
“To map the predicted scores to MOSs, a five-parameter logistic function is applied, which is a standard practice suggested in [49]:”
MethodHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 7×
“Through horizontal comparison, we found that Midjourney has relatively good versatility in different styles, but the versatility of DALLE2 and Stable Diffusion still need to be improved.”
MethodInfluentialGenerative Adversarial Text to Image Synthesis
Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016) · arXiv · doi:10.48550/arxiv.1605.05396 · Cited by 2,494
Zero-shot text-to-image generation
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021) · arXiv · doi:10.48550/arxiv.2102.12092 · Cited by 2,417
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
Xu, T., Zhang, P., Huang, Q., Zhang, H., Gan, Z., Huang, X., & He, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00143 · Cited by 1,923
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357 · cited 8×
“The data shows that Stable Diffusion has a strong tolerance for insufficient iterations, and both quality scores decline by less than 0.1; However, Midjourney’s quality drops significantly after the iteration was halved, especially since the perception score is almost reduced to the level of GLIDE.”
BackgroundMethodInfluentialPick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., & Levy, O. (2023) · neural information processing systems · doi:10.52202/075280-1594 · Cited by 1,352
Convolutional Neural Networks for No-Reference Image Quality Assessment
Kang, L., Ye, P., Li, Y., & Doermann, D. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.224 · Cited by 1,270 · cited 2×
“● DL-based models: This group includes the latest deep learning (DL) metrics, namely DBCNN [58], CLIPIQA [59], CNNIQA [60], HyperNet [61].”
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Hessel, J., Holtzman, A., Forbes, M., Le Bras, R., & Choi, Y. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.595 · Cited by 1,232 · cited 8×
“When it comes to T2I alignment, several metrics represented by Contrastive Language-Image Pre-Training (CLIP) [30]– [32] are widely applied.”
BackgroundMethodInfluentialTalebi, H., & Milanfar, P. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2831899 · Cited by 1,023 · cited 1×
“6 is consistent with previous works [44] [45] about subjective diversity.”
ResultBlind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network
Zhang, W., Ma, K., Yan, J., Deng, D., & Wang, Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2886771 · Cited by 949 · cited 3×
“● DL-based models: This group includes the latest deep learning (DL) metrics, namely DBCNN [58], CLIPIQA [59], CNNIQA [60], HyperNet [61].”
The Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2020) · arXiv · doi:10.48550/arxiv.2004.11138 · Cited by 863
The Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2022) · ACM Computing Surveys · doi:10.1145/3425780 · Cited by 863 · cited 1×
“(c) Deepfake refers to AGIs being recognized as a fake image by HVS because of unreal proportions, lighting [38], etc.”
BackgroundBlindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
Su, S., Yan, Q., Zhu, Y., Zhang, C., Ge, X., Sun, J., & Zhang, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00372 · Cited by 848 · cited 2×
“● DL-based models: This group includes the latest deep learning (DL) metrics, namely DBCNN [58], CLIPIQA [59], CNNIQA [60], HyperNet [61].”
KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment
Hosu, V., Lin, H., Sziranyi, T., & Saupe, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967829 · Cited by 759 · cited 3×
“NSI was obtained from the KonIQ-10k IQA database [35] in the wild, while AGI was collected via the previous AGIQA-1K [13] database and the proposed AGIQA3K database.”
MethodHigh-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
Exploring CLIP for Assessing the Look and Feel of Images
Wang, J., Chan, K. C. K., & Loy, C. C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25353 · Cited by 733
Perceptual image quality assessment: a survey
Zhai, G., & Min, X. (2020) · Science China Information Sciences · doi:10.1007/s11432-019-2757-1 · Cited by 655 · cited 1×
“Therefore, for a single AGI’s quality, the Image Quality Assessment (IQA) [22] method is usually used.”
MethodSelf-citationBlind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features
Xue, W., Mou, X., Zhang, L., Bovik, A. C., & Feng, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2355716 · Cited by 641 · cited 2×
“● SVR-based models: This group includes BMPRI [56], GMLF [57], HIGRADE [58].”
KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment
Hosu, V, Lin, H., Szirányi, T., & Saupe, D. (2020) · SZTAKI Publication Repository (Hungarian Academy of Sciences) · Cited by 512
Blind Image Quality Estimation via Distortion Aggravation
Min, X., Zhai, G., Gu, K., Liu, Y., & Yang, X. (2018) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2018.2816783 · Cited by 508 · cited 2×
“● SVR-based models: This group includes BMPRI [56], GMLF [57], HIGRADE [58].”
Self-citationNo-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency
Golestaneh, S. A., Dadsetan, S., & Kitani, K. M. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv51458.2022.00404 · Cited by 465
CogView: Mastering Text-to-Image Generation via Transformers
Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., Lin, J., Zou, X., Shao, Z., Yang, H., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.13290 · Cited by 450
Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search
Gao, Y., Wang, M., Zha, Z.-J., Shen, J., Li, X., & Wu, X. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2202676 · Cited by 438 · cited 1×
“Considering that there are certain differences between prompt [?], [46] and natural language [47], it is not reasonable to directly use previous word segmentation algorithms [48] to split prompt.”
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
Ying, Z., Niu, H., Gupta, P., Mahajan, D., Ghadiyaram, D., & Bovik, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00363 · Cited by 406
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Yu, J., Xu, Y., Koh, J. Y., Luong, T., Baid, G., Wang, Z., Vasudevan, V., Ku, A., Yang, Y., Ayan, B. K., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.10789 · Cited by 371 · cited 1×
“Since then, AGI has differentiated into two technical routes, namely auto regressive-based models [7]–[9] as CogView, and diffusion-based models like Stable-Diffusion [10]–[12] (SD).”
MethodThe Konstanz natural video database (KoNViD-1k)
Hosu, V., Hahn, F., Jenadeleh, M., Lin, H., Men, H., Sziranyi, T., Li, S., & Saupe, D. (2017) · 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2017.7965673 · Cited by 343 · cited 1×
“A detailed description of these properties can be found in [37].”
BackgroundUncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
Zhang, W., Ma, K., Zhai, G., & Yang, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3061932 · Cited by 327
Self-citationBlind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
Zhang, W., Zhai, G., Wei, Y., Yang, X., & Ma, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01352 · Cited by 325
Self-citationTOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment
Chen, C., Mo, J., Hou, J., Wu, H., Liao, L., Sun, W., Yan, Q., & Lin, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3378466 · Cited by 276
Self-citationScreen Content Quality Assessment: Overview, Benchmark, and Beyond
Min, X., Gu, K., Zhai, G., Yang, X., Zhang, W., Le Callet, P., & Chen, C. W. (2022) · ACM Computing Surveys · doi:10.1145/3470970 · Cited by 246 · cited 1×
“However, considering the complexity of AGI models and the diversity of factors affecting AGIs’ quality, factors affecting the quality of AGIs [13] are different from those of NSIs [23]–[26], and Screen Content Images (SCIs) [27]–[29].”
BackgroundSelf-citationHybrid No-Reference Quality Metric for Singly and Multiply Distorted Images
Gu, K., Zhai, G., Yang, X., & Zhang, W. (2014) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2014.2344471 · Cited by 227 · cited 3×
“II-A reviewed: ● Handcrafted-based models: This group includes four mainstream perceptual quality metrics, namely CEIQ [51], DSIQA [52], NIQE [53], and Sisblim [43].”
Self-citationImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Xu, J., Liu, X., Wu, Y., Tong, Y., Li, Q., Ding, M., Tang, J., & Dong, Y. (2023) · neural information processing systems · doi:10.52202/075280-0700 · Cited by 226
Self-citationSeeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images
Lu, Z., Huang, D., Bai, L., Lu, Z., Wu, C., Liu, X., & Ouyang, W. (2023) · neural information processing systems · doi:10.52202/075280-1105 · Cited by 216 · cited 1×
“6 is consistent with previous works [44] [45] about subjective diversity.”
ResultSelf-citationA no-reference perceptual image sharpness metric based on a cumulative probability of blur detection
Narvekar, N. D., & Karam, L. J. (2009) · 2009 International Workshop on Quality of Multimedia Experience · doi:10.1109/qomex.2009.5246972 · Cited by 208 · cited 2×
“II-A reviewed: ● Handcrafted-based models: This group includes four mainstream perceptual quality metrics, namely CEIQ [51], DSIQA [52], NIQE [53], and Sisblim [43].”
MethodAdversarial text-to-image synthesis: A review
Frolov, S., Hinz, T., Raue, F., Hees, J., & Dengel, A. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.07.019 · Cited by 208 · cited 3×
“According to the statistics [1], [2], there have been at least 20 representative T2I AGI models up to 2023.”
BackgroundSun, W., Min, X., Tu, D., Ma, S., & Zhai, G. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3270621 · Cited by 189 · cited 1×
“However, considering the complexity of AGI models and the diversity of factors affecting AGIs’ quality, factors affecting the quality of AGIs [13] are different from those of NSIs [23]–[26], and Screen Content Images (SCIs) [27]–[29].”
Self-citationHuman Preference Score: Better Aligning Text-to-image Models with Human Preference
Wu, X., Sun, K., Zhu, F., Zhao, R., & Li, H. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00200 · Cited by 188 · cited 4×
“Therefore, we first decompose the prompt into morphemes, so that the objective quality model is more consistent with the subjective perception mechanism.”
BackgroundMethodInfluentialDiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models
Wang, Z. J., Montoya, E., Munechika, D., Yang, H., Hoover, B., & Chau, D. H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.51 · Cited by 171
A Perceptual Quality Assessment Exploration for AIGC Images
Zhang, Z., Li, C., Sun, W., Liu, X., Min, X., & Zhai, G. (2023) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew59549.2023.00082 · Cited by 166 · cited 7×
“AGIQA-1K [13] is the first subjective database for perceptual AGI quality assessment that conducted fine-grained scoring through MOS.”
BackgroundMethodInfluentialSelf-citationAssessing Visual Quality of Omnidirectional Videos
Xu, M., Li, C., Chen, Z., Wang, Z., & Guan, Z. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2886277 · Cited by 161 · cited 1×
“First, we calculate the score correlation within all sessions and remove the outliers as the previous quality database [42], [43].”
MethodSelf-citationNo-Reference Quality Assessment of Contrast-Distorted Images using Contrast EnhancementPreprint
Yan, J., Li, J., & Fu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08879 · Cited by 158 · cited 2×
“II-A reviewed: ● Handcrafted-based models: This group includes four mainstream perceptual quality metrics, namely CEIQ [51], DSIQA [52], NIQE [53], and Sisblim [43].”
MethodA Pathway Towards Responsible AI Generated Content
Lyu, L. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/803 · Cited by 119
Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Borji, A. (2022) · arXiv · doi:10.48550/arxiv.2210.00586 · Cited by 100 · cited 2×
“[36] 2DALLE-2 also applied some diffusion mechanism.”
BackgroundLarge-Scale Crowdsourced Study for Tone-Mapped HDR Pictures
Kundu, D., Ghadiyaram, D., Bovik, A. C., & Evans, B. L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2713945 · Cited by 90
Text-to-image Diffusion Models in Generative AI: A Survey
Zhang, C., Zhang, C., Zhang, M., Kweon, I. S., & Kim, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.07909 · Cited by 82 · cited 4×
“According to the statistics [1], [2], there have been at least 20 representative T2I AGI models up to 2023.”
BackgroundInfluentialPrompt-Based Learning for Unpaired Image Captioning
Zhu, P., Wang, X., Zhu, L., Sun, Z., Zheng, W., Wang, Y., & Chen, C. W. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3265842 · Cited by 71 · cited 1×
“10, which divides the prompt into multiple morphemes while cutting the whole picture into multiple stairs and gives the final score through their one-to-one alignment.”
Hierarchical Feature Aggregation Based on Transformer for Image-Text Matching
Dong, X., Zhang, H., Zhu, L., Nie, L., & Liu, L. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3164230 · Cited by 58 · cited 1×
“The alignment score [40], [41] stands for the compatibility between AGIs and prompts (including all items in the prompt, generally the subject is more critical than detail and style).”
BackgroundJoint Chroma Downsampling and Upsampling for Screen Content Image
Wang, S., Gu, K., Ma, S., & Gao, W. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2461891 · Cited by 46 · cited 1×
“Thus, the reliability of IQA measures is also limited.”
Image Quality Score Distribution Prediction via Alpha Stable Model
Gao, Y., Min, X., Zhu, W., Zhang, X.-P. S., & Zhai, G. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3229839 · Cited by 42 · cited 1×
“6 is consistent with previous works [44] [45] about subjective diversity.”
ResultSelf-citationLearning to Evaluate the Artness of AI-Generated Images
Chen, J., An, J., Lyu, H., Kanan, C., & Luo, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3410672 · Cited by 41 · cited 1×
“The performance of an AGI model) or style transfer [21], which is unsuitable for evaluating the perceptual quality of only one image.”
VDPVE: VQA Dataset for Perceptual Video Enhancement
Gao, Y., Cao, Y., Kou, T., Sun, W., Dong, Y., Liu, X., Min, X., & Zhai, G. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00152 · Cited by 36 · cited 1×
“However, considering the complexity of AGI models and the diversity of factors affecting AGIs’ quality, factors affecting the quality of AGIs [13] are different from those of NSIs [23]–[26], and Screen Content Images (SCIs) [27]–[29].”
Self-citationDiscrete Joint Semantic Alignment Hashing for Cross-Modal Image-Text Search
Wang, S., Zhao, H., & Li, K. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3186714 · Cited by 30 · cited 1×
“The alignment score [40], [41] stands for the compatibility between AGIs and prompts (including all items in the prompt, generally the subject is more critical than detail and style).”
BackgroundLight-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement
Dong, Y., Liu, X., Gao, Y., Zhou, X., Tan, T., & Zhai, G. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611923 · Cited by 29 · cited 1×
“However, considering the complexity of AGI models and the diversity of factors affecting AGIs’ quality, factors affecting the quality of AGIs [13] are different from those of NSIs [23]–[26], and Screen Content Images (SCIs) [27]–[29].”
BackgroundSelf-citationRectified Wasserstein Generative Adversarial Networks for Perceptual Image Restoration
Ma, H., Liu, D., & Wu, F. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3185316 · Cited by 29 · cited 1×
“Generative Adversarial Networks [3] (GAN)-based models, such as Text-conditional GAN [4]–[6] series, are the earliest end-to-end AGI model from character level to the pixel level.”
MethodA Real-Time Blind Quality-of-Experience Assessment Metric for HTTP Adaptive Streaming
Li, C., Lim, M. L., Bentaleb, A., & Zimmermann, R. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00286 · Cited by 21 · cited 9×
“The distributions include NSIs in the KonIQ-10k [35], previous AGIs in the AGIQA-1K [13] and latest AGIs in the proposed AGIQA-3K database.”
BackgroundInfluentialSelf-citationHe, J., Gao, Y., Zhang, T., Zhang, Z., & Wu, F. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00284 · Cited by 16 · cited 1×
“Considering that there are certain differences between prompt [?], [46] and natural language [47], it is not reasonable to directly use previous word segmentation algorithms [48] to split prompt.”
Self-citationA Full- Reference Quality Assessment Metric for Cartoon Images
Li, C., Zhang, Z., Sun, W., Min, X., & Zhai, G. (2022) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp55362.2022.9949270 · Cited by 14 · cited 1×
“However, considering the complexity of AGI models and the diversity of factors affecting AGIs’ quality, factors affecting the quality of AGIs [13] are different from those of NSIs [23]–[26], and Screen Content Images (SCIs) [27]–[29].”
BackgroundSelf-citationChen, Y., Liu, L., & Ding, C. (2023) · arXiv · doi:10.48550/arxiv.2305.10843 · Cited by 9
Cited by
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment
Chen, C., Mo, J., Hou, J., Wu, H., Liao, L., Sun, W., Yan, Q., & Lin, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3378466 · Cited by 276
Self-citationPerceptual video quality assessment: a survey
Min, X., Duan, H., Sun, W., Zhu, Y., & Zhai, G. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4133-3 · Cited by 218
Self-citationQuality assessment in the era of large models: A survey
Zhang, Z., Zhou, Y., Li, C., Zhao, B., Liu, X., & Zhai, G. (2025) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3722559 · Cited by 23
Self-citationWu, X., Hao, Y., Sun, K., Chen, Y., Zhu, F., Zhao, R., & Li, H. (2023) · arXiv · doi:10.48550/arxiv.2306.09341 · Cited by 22
Metadata
- Authors
- Li, C., Zhang, Z., Wu, H., Sun, W., Min, X., Liu, X., Zhai, G., & Lin, W.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2024-08
- Volume
- 34
- Issue
- 8
- Pages
- 6833-6846
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W4387010079
- Cited by
- 180
- References
- 67
- FWCI
- 16.37
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.