{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:48:15Z","timestamp":1785912495192,"version":"3.56.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":[[2026,3]]},"DOI":"10.1109\/wacvw68408.2026.00114","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:15:07Z","timestamp":1785870907000},"page":"1038-1047","source":"Crossref","is-referenced-by-count":0,"title":["We Still See Broken Limbs: Towards Anatomical Realism in GenAI Via Human Preference Learning"],"prefix":"10.1109","author":[{"given":"Stephanie","family":"K\u00e4s","sequence":"first","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Sch\u00f6nherr","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Adding Conditional Control to Textto-Image Diffusion Models","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2098"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32808"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00043"},{"key":"ref7","article-title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarseto-fine Pose-Reversible Guidance","author":"Fang","year":"2024","journal-title":"ECCV"},{"key":"ref8","article-title":"Detecting Human Artifacts from Text-to-Image Models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation","author":"Andreou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref11","article-title":"AlignProp: Reinforcement Learning for Aligning Diffusion Models with Human Feedback","author":"Prabhudesai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Training Diffusion Models with Reinforcement Learning","author":"Black","year":"2024","journal-title":"ICLR Poster"},{"key":"ref13","article-title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","author":"Clark","year":"2026","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref15","article-title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","author":"Prabhudesai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref18","article-title":"Multi-HMR: Multi-Person WholeBody Human Mesh Recovery in a Single Shot","author":"Baradel","year":"2024","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC56324.2022.10065997"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"ref24","article-title":"LAION-Aesthetics: A LargeScale Aesthetic Quality Dataset","author":"Schuhmann","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref27","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Generative Modeling by Estimating Gradients of the Data Distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Score-Based Generative Modeling through Stochastic Differential Equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref30","article-title":"Improved Denoising Diffusion Probabilistic Models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref31","article-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","author":"Nichol","year":"2022","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref35","article-title":"Generative Adversarial Nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Improved Techniques for Training GANs","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref37","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Demystifying MMD GANs","author":"Binkowski","year":"2018","journal-title":"ICLR"},{"key":"ref39","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref41","article-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref42","article-title":"Stable Diffusion 3","year":"2024","journal-title":"Tech. Rep."},{"key":"ref43","article-title":"Introducing Flux.1","author":"Forest Labs","year":"2024","journal-title":"Tech. Rep."},{"key":"ref44","article-title":"ChatGPT-5: Large-Scale Multimodal Language Model","year":"2025","journal-title":"Tech. Rep."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680693"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32808"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00043"},{"key":"ref50","article-title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarseto-Fine Pose-Reversible Guidance","author":"Fang","year":"2024","journal-title":"ECCV"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01977"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2584"},{"key":"ref53","article-title":"EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"TIFA: Accurate and Interpretable Textto-Image Faithfulness Evaluation with Question Answering","author":"Hu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617369\/11617396\/11617772.pdf?arnumber=11617772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:08:08Z","timestamp":1785910088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617772\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/wacvw68408.2026.00114","relation":{},"subject":[],"published":{"date-parts":[[2026,3]]}}}