{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:47:21Z","timestamp":1770695241265,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","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\/978-981-95-6957-1_14","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:44Z","timestamp":1770633884000},"page":"190-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VENUS: Visual Editing with\u00a0Noise Inversion Using Scene Graphs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8403-1240","authenticated-orcid":false,"given":"Thanh-Nhan","family":"Vo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7729-2927","authenticated-orcid":false,"given":"Trong-Thuan","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0236-7992","authenticated-orcid":false,"given":"Tam V.","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Brack, M., et al.: Ledits++: limitless image editing using text-to-image models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8861\u20138870 (2024)","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: Masactrl: tuning-free mutual self-attention control for consistent image synthesis and editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22560\u201322570 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Dhamo, H., et al.: Semantic image manipulation using scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5213\u20135222 (2020)","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"14_CR6","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J.M., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv abs\/2208.01626 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251252882"},{"key":"14_CR7","unstructured":"Ho, J.: Classifier-free diffusion guidance. arXiv abs\/2207.12598 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249145348"},{"key":"14_CR8","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"14_CR10","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: PNP inversion: boosting diffusion-based editing with 3 lines of code. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: Diffusionclip: text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"14_CR13","doi-asserted-by":"publisher","unstructured":"Korhonen, J., You, J.: Peak signal-to-noise ratio revisited: is simple is beautiful? (2012). https:\/\/doi.org\/10.1109\/QoMEX.2012.6263880","DOI":"10.1109\/QoMEX.2012.6263880"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: European Conference on Computer Vision, pp. 728\u2013755. Springer (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Tripathi, S., Du, B., Guha, T., Nguyen, T.Q.: In defense of scene graphs for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1407\u20131416 (2021)","DOI":"10.1109\/ICCV48922.2021.00144"},{"key":"14_CR17","unstructured":"Qin, J., et al.: Diffusiongpt: LLM-driven text-to-image generation system. arXiv preprint arXiv:2401.10061 (2024)"},{"key":"14_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR20","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: llama for scalable image generation. arXiv preprint arXiv:2406.06525 (2024)"},{"key":"14_CR21","unstructured":"Team, Q.: Qwen2.5-vl (2025). https:\/\/qwenlm.github.io\/blog\/qwen2.5-vl\/"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Vo, T.N., Nguyen, T.T., Nguyen, T.V., Tran, M.T.: Saturn: autoregressive image generation guided by scene graphs. In: Proceedings of the International Conference on Multimedia Analysis and Pattern Recognition (MAPR) (2025)","DOI":"10.1109\/MAPR67746.2025.11133881"},{"key":"14_CR24","first-page":"128374","volume":"37","author":"Z Wang","year":"2024","unstructured":"Wang, Z., Li, A., Li, Z., Liu, X.: Genartist: multimodal LLM as an agent for unified image generation and editing. Adv. Neural. Inf. Process. Syst. 37, 128374\u2013128395 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhao, L., Xing, W.: Stylediffusion: controllable disentangled style transfer via diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7677\u20137689 (2023)","DOI":"10.1109\/ICCV51070.2023.00706"},{"issue":"4","key":"14_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR27","unstructured":"Yang, L., et al.: Diffusion-based scene graph to image generation with masked contrastive pre-training. arXiv preprint arXiv:2211.11138 (2022)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Yoon, S., et al.: Image-to-image retrieval by learning similarity between scene graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 10718\u201310726 (2021)","DOI":"10.1609\/aaai.v35i12.17281"},{"key":"14_CR29","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Chen, D., Liao, J.: Sgedit: bridging LLM with text2image generative model for scene graph-based image editing. arXiv preprint arXiv:2410.11815 (2024)","DOI":"10.1145\/3687957"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:52Z","timestamp":1770633892000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_14","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 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}