{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T21:03:26Z","timestamp":1790111006485,"version":"4.0.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109346","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T12:46:42Z","timestamp":1783601202000},"page":"109346","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["PiGIE: Proximal policy optimization guided diffusion for fine-grained image editing"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6496-355X","authenticated-orcid":false,"given":"Tiancheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxiu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9647-3991","authenticated-orcid":false,"given":"Weijian","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2701-4764","authenticated-orcid":false,"given":"Huajun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5378-6404","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109346_bib0001","series-title":"2022 IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","article-title":"Blended diffusion for text-driven editing of natural images","author":"Avrahami","year":"2022"},{"key":"10.1016\/j.neunet.2026.109346_bib0002","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"18187","article-title":"Blended diffusion for text-driven editing of natural images","author":"Avrahami","year":"2022"},{"key":"10.1016\/j.neunet.2026.109346_bib0003","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., & Levine, S. (2023). Training diffusion models with reinforcement learning. arXiv preprint arXiv: 2305.13301."},{"key":"10.1016\/j.neunet.2026.109346_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18392","article-title":"Instructpix2pix: Learning to follow image editing instructions","author":"Brooks","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0005","unstructured":"Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Tom, H., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E. J., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., & Amodei, D. (2020). Language models are few-shot learners. Advancesin Neural Information Processing Systems, 33, 1877\u20131901."},{"key":"10.1016\/j.neunet.2026.109346_bib0006","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"22560","article-title":"MasaCtrl: Tuning-free mutual self-attention control for consistent image synthesis and editing","author":"Cao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0007","series-title":"2021 IEEE\/CVF international conference on computer vision (ICCV)","first-page":"9580","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.neunet.2026.109346_bib0008","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., & Zhao, R. (2023). Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv: 2306.15195."},{"key":"10.1016\/j.neunet.2026.109346_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"38038","article-title":"EditMGT: Unleashing potentials of masked generative transformers in image editing","author":"Chow","year":"2026"},{"key":"10.1016\/j.neunet.2026.109346_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7423","article-title":"PRDP: Proximal reward difference prediction for large-scale reward finetuning of diffusion models","author":"Deng","year":"2024"},{"key":"10.1016\/j.neunet.2026.109346_bib0011","series-title":"Advances in neural information processing systems","first-page":"16222","article-title":"Diffusion self-guidance for controllable image generation","volume":"vol. 36","author":"Epstein","year":"2023"},{"issue":"2","key":"10.1016\/j.neunet.2026.109346_bib0012","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109346_bib0013","series-title":"Advances in neural information processing systems","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume":"vol. 36","author":"Fan","year":"2024"},{"key":"10.1016\/j.neunet.2026.109346_bib0014","unstructured":"Fu, T.-J., Hu, W., Du, X., Wang, W. Y., Yang, Y., & Gan, Z. (2023). Guiding instruction-based image editing via multimodal large language models. arXiv preprint arXiv: 2309.17102."},{"key":"10.1016\/j.neunet.2026.109346_bib0015","series-title":"European conference on computer vision","first-page":"717","article-title":"Language-driven artistic style transfer","author":"Fu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109346_bib0016","series-title":"Generative adversarial networks","volume":"vol. 63","author":"Goodfellow","year":"2020"},{"key":"10.1016\/j.neunet.2026.109346_bib0017","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2022). Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv: 2208.01626."},{"key":"10.1016\/j.neunet.2026.109346_bib0018","series-title":"Advances in neural information processing systems","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"vol. 33","author":"Ho","year":"2020"},{"key":"10.1016\/j.neunet.2026.109346_bib0019","unstructured":"Ho, J., & Salimans, T. (2022). Classifier-free diffusion guidance. arXiv preprint arXiv: 2207.12598."},{"key":"10.1016\/j.neunet.2026.109346_bib0020","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1109\/TNNLS.2023.3342645","article-title":"DiffStyler: Controllable dual diffusion for text-driven image stylization","volume":"36","author":"Huang","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109346_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106777","article-title":"PFB-diff: Progressive feature blending diffusion for text-driven image editing","volume":"181","author":"Huang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109346_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6007","article-title":"Imagic: Text-based real image editing with diffusion models","author":"Kawar","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0023","series-title":"2022 IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"2648","article-title":"DiffusionClip: Text-guided diffusion models for robust image manipulation","author":"Kim","year":"2022"},{"key":"10.1016\/j.neunet.2026.109346_bib0024","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109346_bib0025","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109346_bib0026","series-title":"2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"ManiGAN: Text-guided image manipulation","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2026.109346_bib0027","series-title":"Proceedings of the european conference on computer vision (eccv)","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109346_bib0028","series-title":"Advances in neural information processing systems","article-title":"Visual instruction tuning","volume":"vol. 36","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109346_bib0029","doi-asserted-by":"crossref","unstructured":"Liu, X., Lin, Z., Zhang, J., Zhao, H., Tran, Q., Wang, X., & Li, H. (2020). Open-edit: Open-domain image manipulation with open-vocabulary instructions. arXiv preprint arXiv: 2008.03922.","DOI":"10.1007\/978-3-030-58621-8_6"},{"key":"10.1016\/j.neunet.2026.109346_bib0030","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv: 1711.05101."},{"key":"10.1016\/j.neunet.2026.109346_bib0031","unstructured":"Meng, C., Song, Y., Song, J., Wu, J., Zhu, J.-Y., & Ermon, S. (2021). SDEdit: Image synthesis and editing with stochastic differential equations. arXiv preprint arXiv: 2108.01630."},{"key":"10.1016\/j.neunet.2026.109346_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6038","article-title":"Null-text inversion for editing real images using guided diffusion models","author":"Mokady","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0033","series-title":"Acm siggraph 2023 conference proceedings","first-page":"1","article-title":"Zero-shot image-to-image translation","author":"Parmar","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"01036","article-title":"Diffusion autoencoders: Toward a meaningful and decodable representation","author":"Preechakul","year":"2022"},{"key":"10.1016\/j.neunet.2026.109346_bib0035","unstructured":"Radford, A., Kim, J., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In PmLR (pp. 8748\u20138763)."},{"key":"10.1016\/j.neunet.2026.109346_bib0036","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016). Generative adversarial text to image synthesis. arXiv preprint arXiv: 1605.05396."},{"key":"10.1016\/j.neunet.2026.109346_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (cvpr)","first-page":"01042","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109346_bib0038","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv: 1707.06347."},{"key":"10.1016\/j.neunet.2026.109346_bib0039","unstructured":"Shen, E. J., Wallis, Y., Allen-Zhu, Z., Li, Y., Wang, S., & Chen, W. (2021). Lora: Low-rank adaptation of large language models. arXiv preprint arXiv: 2106.09685."},{"key":"10.1016\/j.neunet.2026.109346_bib0040","unstructured":"Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In PMLR (pp. 2256\u20132265)."},{"key":"10.1016\/j.neunet.2026.109346_bib0041","series-title":"International conference on learning representations","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2026.109346_bib0042","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"7677","article-title":"StyleDiffusion: Controllable disentangled style transfer via diffusion models","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22428","article-title":"SmartBrush: Text and shape guided object inpainting with diffusion model","author":"Xie","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0044","unstructured":"Yildirim, A. B., Baday, V., Erdem, E., Erdem, A., & Dundar, A. (2023). Inst-inpaint: Instructing to remove objects with diffusion models. arXiv preprint arXiv: 2304.03246."},{"key":"10.1016\/j.neunet.2026.109346_bib0045","series-title":"Advances in neural information processing systems","article-title":"MagicBrush: A manually annotated dataset for instruction-guided image editing","volume":"vol. 36","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109346_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9026","article-title":"Hive: Harnessing human feedback for instructional visual editing","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109346_bib0047","unstructured":"Zhang, X., Guo, J., Yoo, P., Matsuo, Y., & Iwasawa, Y. (2023a). Paste, inpaint and harmonize via denoising: subject-driven image editing with pre-trained diffusion model. arXiv preprint arXiv: 2306.07596."},{"key":"10.1016\/j.neunet.2026.109346_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6027","article-title":"Sine: Single image editing with text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109346_bib0049","series-title":"Advances in neural information processing systems","first-page":"139195","article-title":"Enabling instructional image editing with in-context generation in large scale diffusion transformer","volume":"vol. 38","author":"Zhang","year":"2026"},{"key":"10.1016\/j.neunet.2026.109346_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106541","article-title":"LD-CSNet: A latent diffusion-based architecture for perceptual compressed sensing","volume":"179","author":"Zheng","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109346_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106818","article-title":"Cut-and-paste: Subject-driven video editing with attention control","volume":"181","author":"Zuo","year":"2025","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008051?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026008051?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T20:01:07Z","timestamp":1790107267000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026008051"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":51,"alternative-id":["S0893608026008051"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109346","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PiGIE: Proximal policy optimization guided diffusion for fine-grained image editing","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109346","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109346"}}