{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:29Z","timestamp":1777889669707,"version":"3.51.4"},"reference-count":101,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01435","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15469-15480","source":"Crossref","is-referenced-by-count":0,"title":["IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models"],"prefix":"10.1109","author":[{"given":"Khaled","family":"Abud","sequence":"first","affiliation":[{"name":"MSU Institute for Artificial Intelligence,Moscow,Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Lavrushkin","sequence":"additional","affiliation":[{"name":"MSU Institute for Artificial Intelligence,Moscow,Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Kirillov","sequence":"additional","affiliation":[{"name":"Lomonosov Moscow State University,Moscow,Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitriy","family":"Vatolin","sequence":"additional","affiliation":[{"name":"MSU Institute for Artificial Intelligence,Moscow,Russian Federation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref2","author":"Schuhmann","year":"2023","journal-title":"Laion aesthetics predictor"},{"key":"ref3","volume-title":"Improving image generation with better captions","author":"Betker","year":"2023"},{"key":"ref4","volume-title":"Black Forest Labs. Flux github repo","year":"2024"},{"key":"ref5","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref7","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref9","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00200"},{"key":"ref12","article-title":"Dp-iqa: Utilizing diffusion prior for blind image quality assessment in the wild","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Genziqa: Generalized image quality assessment using prompt-guided latent diffusion models","author":"De","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32530"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3523800"},{"key":"ref16","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"In International conference on machine learning","author":"Ramesh"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref19","article-title":"Playground v3: Improving text-toimage alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Yaart: Yet another art rendering technology","author":"Kastryulin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Imagen 3","author":"Baldridge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref25","article-title":"LoRA: Low-rank adaptation of large language models","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref27","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2023","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref29","article-title":"Erasing concepts from diffusion models. In ECCV","author":"Gandikota","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Stylecrafter: Enhancing stylized text-to-video generation with style adapter","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref35","first-page":"2117","article-title":"A visual information fidelity approach to video quality assessment","volume-title":"In The first international workshop on video processing and quality metrics for consumer electronics","volume":"7","author":"Sheikh","year":"2005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2147325"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref42","article-title":"A Deep Bilinear Convolutional Neural Network","journal-title":"Blind image quality assessment using a deep bilinear convolutional neural network"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01352"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref46","first-page":"11911200","article-title":"Maniqa: Multi-dimension attention network for noreference image quality assessment","author":"Yang","year":"2022","journal-title":"CVPR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_37"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13344"},{"key":"ref60","article-title":"Vmix: Improving text-to-image diffusion model with cross-attention mixing control","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.1"},{"key":"ref62","volume-title":"Damian Stewart. Compel library","year":"2023"},{"key":"ref63","article-title":"Diffusion models beat gans on image synthesis","volume-title":"In Proceedings of the 35th International Conference on Neural Information Processing Systems, NIPS \u201921","volume":"3","author":"Dhariwal","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref65","volume-title":"Hinton. Layer normalization","author":"Lei Ba","year":"2016"},{"key":"ref66","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref68","volume-title":"Laion-5b 170k subset of images with aesthetics score > 6.5","author":"Desai","year":"2022"},{"key":"ref69","article-title":"Laion-5b: an open large-scale dataset for training next generation image-text models","volume-title":"NIPS \u201922","author":"Schuhmann","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01352"},{"key":"ref76","author":"Santana","year":"2024","journal-title":"Dataset of user-generated prompts collected from lexica.art website"},{"key":"ref77","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","journal-title":"Transactions on Machine Learning Research, 2022. Featured Certification"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref80","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref81","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref83","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"In International Conference on Learning Representations","author":"Meng","year":"2022"},{"key":"ref84","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ICML\u201923. JMLR.org","author":"Li"},{"key":"ref85","volume-title":"Jacob Gildenblat and contributors. Pytorch library for cam methods","year":"2021"},{"key":"ref86","volume-title":"IQA-PyTorch: Pytorch toolbox for image quality assessment","author":"Chen","year":"2022"},{"key":"ref87","author":"ye","year":"2023","journal-title":"calflops: a flops and params calculate tool for neural networks in pytorch framework"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881959"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1117\/1.3267105"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2053549"},{"key":"ref91","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","volume-title":"arXiv preprint","author":"Wu","year":"2023"},{"key":"ref92","volume-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"ref93","author":"Paszke","year":"2017","journal-title":"Automatic differentiation in pytorch"},{"key":"ref94","volume-title":"Accelerate: Training and inference at scale made simple, efficient and adaptable","author":"Gugger","year":"2022"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref97","article-title":"A study on the evaluation of generative models","author":"Betzalel","year":"2022","journal-title":"arXiv preprint"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"ref101","volume":"11","author":"Borisov","year":"2023","journal-title":"Msu video super-resolution quality metrics benchmark 2023"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445141.pdf?arnumber=11445141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:49Z","timestamp":1777612549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":101,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01435","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}