{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T08:06:44Z","timestamp":1788941204455,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370402","type":"print"},{"value":"9783032370419","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37041-9_27","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:27:00Z","timestamp":1788938820000},"page":"509-526","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Q-REAL: Towards Naturalness and\u00a0Distortion Evaluation for\u00a0AI-Generated Content"],"prefix":"10.1007","author":[{"given":"Shushi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liya","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengjiao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuezhi","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"27_CR1","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. In: arXiv preprint arXiv:2511.21631 (2025)"},{"key":"27_CR2","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report. In: arXiv preprint arXiv:2502.13923 (2025)"},{"key":"27_CR3","unstructured":"Bandyopadhyay, H., Entezari, R., Scott, J., Adithyan, R., Song, Y.Z., Jampani, V.: Sd3.5-flash: distribution-guided distillation of generative flows. arXiv:2509.21318 arXiv preprint (2025)"},{"key":"27_CR4","unstructured":"Black-Forest-Labs (2025). https:\/\/bfl.ai\/models\/flux-pro"},{"key":"27_CR5","unstructured":"Cao, S., et al.: Artimuse: fine-grained image aesthetics assessment with joint scoring and expert-level understanding. In: arXiv preprint arXiv:2507.14533 (2025)"},{"key":"27_CR6","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. In: arXiv preprint arXiv:2412.05271 (2024)"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Grounding-IQA: multimodal language grounding model for image quality assessment. In: arXiv preprint arXiv:2411.17237 (2024)","DOI":"10.32388\/074NKV"},{"key":"27_CR8","unstructured":"DeepMind, G.: (2026). https:\/\/deepmind.google\/models\/gemini\/pro\/"},{"key":"27_CR9","unstructured":"DreaminaAI: (2025). https:\/\/dreamina.capcut.com\/"},{"key":"27_CR10","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. In: Advances in Neural Information Processing Systems (2014)"},{"key":"27_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems (2020)"},{"key":"27_CR12","unstructured":"Ji, Y., et al.: Fakexplain: AI-generated image detection via human-aligned grounded reasoning. In: International Conference on Learning Representations (2026)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, D., et al.: Genai arena: an open evaluation platform for generative models. arXiv:2406.04485 arXiv preprint (2024)","DOI":"10.52202\/079017-2538"},{"key":"27_CR14","unstructured":"Journal, E.: AI image statistics for 2024: how much content was created by AI. In: Everypixel (2024)"},{"key":"27_CR15","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation. In: Advances in Neural Information Processing Systems (2020)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., et\u00a0al.: Aigiqa-20k: a large database for ai-generated image quality assessment. In: arXiv preprint arXiv:2404.03407 (2024)","DOI":"10.1109\/CVPRW63382.2024.00636"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: AGIQA-3k: an open database for AI-generated image quality assessment. In: IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"27_CR18","unstructured":"Li, F., et al.: Llava-next-interleave: tackling multi-image, video, and 3d in large multimodal models. In: arXiv preprint arXiv:2407.07895 (2024)"},{"key":"27_CR19","unstructured":"Liang, Y., et al.: Rich human feedback for text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding Dino: Marrying Dino with grounded pre-training for open-set object detection. In: arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Ma, Y., Wu, X., Sun, K., Li, H.: Hpsv3: towards wide-spectrum human preference score. In: International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.01400"},{"key":"27_CR22","unstructured":"Meng, X., Zhang, Z., Zhang, Z., Liao, J., Qin, L., Wang, W.: Identity-grpo: optimizing multi-human identity-preserving video generation via reinforcement learning. In: arXiv preprint arXiv:2510.14256 (2025)"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Mittal, A., Soundararajan, A.K., Bovik, A.C.: Making a \u2018completely blind\u2019 image quality analyzer. IEEE Signal Process. Lett. (2013)","DOI":"10.1109\/LSP.2012.2227726"},{"key":"27_CR24","unstructured":"OpenAI: (2024). https:\/\/openai.com\/index\/gpt-4o"},{"key":"27_CR25","unstructured":"OpenAI: (2026). https:\/\/developers.openai.com\/api\/docs\/models\/gpt-5.4"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Peng, F., et al.: AIGC image quality assessment via image-prompt correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2024)","DOI":"10.1109\/CVPRW63382.2024.00644"},{"key":"27_CR27","unstructured":"Rafael, C., Wintz, G., P.: Digital Image Processing. Addison-Wesley Longman Publishing (1987)"},{"key":"27_CR28","unstructured":"Team, K.: Kolors: effective training of diffusion model for photorealistic text-to-image synthesis (2025)"},{"key":"27_CR29","unstructured":"Techreport: AI image generator market statistics in 2024. In: Techreport (2024)"},{"key":"27_CR30","unstructured":"Thakur, A.S., Choudhary, K., Ramayapally, V.S.: Judging the judges: evaluating alignment and vulnerabilities in LLMs-as-judges. arXiv:2406.12624 arXiv preprint (2024)"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: scalable image generation via next-scale prediction. arXiv:2404.02905 arXiv preprint (2024)","DOI":"10.52202\/079017-2694"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring clip for assessing the look and feel of images. In: AAAI Conference on Artificial Intelligence (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. arXiv:2201.11903 arXiv preprint (2023)","DOI":"10.52202\/068431-1800"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Q-instruct: improving low-level visual abilities for multi-modality foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"27_CR35","unstructured":"Wu, H., et al.: Q-align: teaching LMMs for visual scoring via discrete text-defined levels. In: arXiv preprint arXiv:2312.17090 (2023)"},{"key":"27_CR36","unstructured":"Wu, X., et al.: Human preference score v2: a solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv:2306.09341 arXiv preprint (2023)"},{"key":"27_CR37","unstructured":"Xiao, Y., et al.: Unveiling perceptual artifacts: a fine-grained benchmark for interpretable AI-generated image detection. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-0700"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"You, Z., Cai, X., Gu, J., Xue, T., Dong, C.: Teaching large language models to regress accurate image quality scores using score distribution. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.01350"},{"key":"27_CR40","unstructured":"Zhang, P., et al.: Internlmxcomposer: a vision-language large model for advanced text-image comprehension and composition. In: arXiv preprint arXiv:2309.15112 (2023)"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"27_CR42","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with Bert. In: International Conference on Learning Representations (2020)"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, W., Ma, K., Yan, J., Deng, D., Wang, Z.: Blind image quality assessment using a deep bilinear convolutional neural network. In: IEEE Transactions on Circuits and Systems for Video Technology (2020)","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhai, G., Wei, Y., Yang, X., Ma, K.: Blind image quality assessment via vision-language correspondence: a multitask learning perspective. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"27_CR45","unstructured":"Zhang, Z., et al.: Q-bench-video: benchmarking the video quality understanding of LMMs. In: arXiv preprint arXiv:2409.20063 (2024)"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Q-eval-100k: evaluating visual quality and alignment level for text-to-vision content. In: arXiv preprint arXiv:2503.02357 (2025)","DOI":"10.1109\/CVPR52734.2025.00993"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Q-boost: on visual quality assessment ability of low-level multi-modality foundation models. In: arXiv preprint arXiv:2312.15300 (2023)","DOI":"10.1109\/ICMEW63481.2024.10645451"},{"key":"27_CR48","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv:2504.10479 arXiv preprint (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37041-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:27:13Z","timestamp":1788938833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37041-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370402","9783032370419"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37041-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}