{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:19:28Z","timestamp":1765041568088,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726699"},{"type":"electronic","value":"9783031726705"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72670-5_18","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"314-330","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Responsible Visual Editing"],"prefix":"10.1007","author":[{"given":"Minheng","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeli","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2Stylegan++: how to edit the embedded images? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8296\u20138305 (2020)","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"18_CR3","unstructured":"Brack, M., Friedrich, F., Hintersdorf, D., Struppek, L., Schramowski, P., Kersting, K.: SEGA: instructing text-to-image models using semantic guidance. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"18_CR4","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":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Shen, Y., Gao, J., Liu, J., Liu, X.: Language-based image editing with recurrent attentive models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8721\u20138729 (2018)","DOI":"10.1109\/CVPR.2018.00909"},{"key":"18_CR7","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Dong, H., Yu, S., Wu, C., Guo, Y.: Semantic image synthesis via adversarial learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5706\u20135714 (2017)","DOI":"10.1109\/ICCV.2017.608"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. arXiv preprint arXiv:2303.07345 (2023)","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Orgad, H., Belinkov, Y., Materzy\u0144ska, J., Bau, D.: Unified concept editing in diffusion models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5111\u20135120 (2024)","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Geng, Z., et\u00a0al.: InstructDiffusion: a generalist modeling interface for vision tasks. arXiv preprint arXiv:2309.03895 (2023)","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"18_CR12","unstructured":"Heng, A., Soh, H.: Continual learning for forgetting in deep generative models (2023)"},{"key":"18_CR13","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE\/CVF Conference on Cmputer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Wang, S.Y., Shechtman, E., Zhang, R., Zhu, J.Y.: Ablating concepts in text-to-image diffusion models (2023). http:\/\/arxiv.org\/abs\/2303.13516, arXiv:2303.13516","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Wang, S.Y., Shechtman, E., Zhang, R., Zhu, J.Y.: Ablating concepts in text-to-image diffusion models. arXiv preprint arXiv:2303.13516 (2023)","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"18_CR18","unstructured":"Li, F., et al.: Semantic-SAM: segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767 (2023)"},{"key":"18_CR19","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Ni, M., Li, X., Zuo, W.: NUWA-LIP: Language-guided image inpainting with defect-free VQGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14183\u201314192 (2023)","DOI":"10.1109\/CVPR52729.2023.01363"},{"key":"18_CR21","unstructured":"Ni, M., et al.: ORES: open-vocabulary responsible visual synthesis. arXiv preprint arXiv:2308.13785 (2023)"},{"key":"18_CR22","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"18_CR23","unstructured":"OpenAI: ChatGPT (2022). https:\/\/chat.openai.com"},{"key":"18_CR24","unstructured":"OpenAI: DALL-E 3 (2023). https:\/\/openai.com\/dall-e-3"},{"key":"18_CR25","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"18_CR26","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"18_CR27","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"18_CR28","unstructured":"Rando, J., Paleka, D., Lindner, D., Heim, L., Tram\u00e8r, F.: Red-teaming the stable diffusion safety filter. arXiv preprint arXiv:2210.04610 (2022)"},{"key":"18_CR29","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":"18_CR30","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., Kersting, K.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22522\u201322531 (2023)","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"18_CR31","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Wang, S.Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: CNN-generated images are surprisingly easy to spot... for now. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8695\u20138704 (2020)","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"18_CR33","unstructured":"Yang, J., Zhang, H., Li, F., Zou, X., Li, C., Gao, J.: Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V. arXiv preprint arXiv:2310.11441 (2023)"},{"key":"18_CR34","unstructured":"Yu, T., et al.: Inpaint anything: segment anything meets image inpainting. arXiv preprint arXiv:2304.06790 (2023)"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, E., Wang, K., Xu, X., Wang, Z., Shi, H.: Forget-me-not: learning to forget in text-to-image diffusion models. arXiv preprint arXiv:2303.17591 (2023)","DOI":"10.1109\/CVPRW63382.2024.00182"},{"key":"18_CR36","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: ControlVideo: training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72670-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:20:00Z","timestamp":1732828800000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72670-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726699","9783031726705"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72670-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}