{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:02:04Z","timestamp":1789718524543,"version":"4.0.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","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\/978-3-032-37174-4_5","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:08:19Z","timestamp":1789715299000},"page":"72-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantically Aligned Gradient-Driven Context-Preserving Image Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-1255","authenticated-orcid":false,"given":"Chiranjeev","family":"Chiranjeev","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7451-3317","authenticated-orcid":false,"given":"Muskan","family":"Dosi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5952-2274","authenticated-orcid":false,"given":"Mayank","family":"Vatsa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4060-4573","authenticated-orcid":false,"given":"Richa","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"5_CR1","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report (2025)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9630\u20139640 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"5_CR4","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"5_CR5","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: Diffedit: diffusion-based semantic image editing with mask guidance. In: ICLR (2023)"},{"key":"5_CR6","unstructured":"Deng, C., et al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: CVPR, pp. 4685\u20134694 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"5_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. NeurIPS 34, 8780\u20138794 (2021)","journal-title":"NeurIPS"},{"key":"5_CR9","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: ICML, pp. 12606\u201312633 (2024)"},{"key":"5_CR10","unstructured":"Fu, T.J., Hu, W., Du, X., Wang, W., Yang, Y., Gan, Z.: Guiding instruction-based image editing via multimodal large language models. In: ICLR, pp. 54820\u201354833 (2024)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Geng, Z., et al.: Instructdiffusion: a generalist modeling interface for vision tasks. In: CVPR, pp. 12709\u201312720 (2024)","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"5_CR12","unstructured":"Gu, X., et al.: Multi-reward as condition for instruction-based image editing. In: ICLR, pp. 82243\u201382262 (2025)"},{"key":"5_CR13","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"key":"5_CR14","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Smartedit: exploring complex instruction-based image editing with multimodal large language models. In: CVPR, pp. 8362\u20138371 (2024)","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"5_CR16","unstructured":"Hui, M., et al.: HQ-edit: a high-quality dataset for instruction-based image editing. In: Yue, Y., Garg, A., Peng, N., Sha, F., Yu, R. (eds.) International Conference on Learning Representations, pp. 73407\u201373424 (2025)"},{"key":"5_CR17","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"5_CR18","unstructured":"Labs, B.F., et al.: Flux. 1 Kontext: flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742 (2025)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Superedit: rectifying and facilitating supervision for instruction-based image editing. In: ICCV, pp. 19206\u201319215 (2025)","DOI":"10.1109\/ICCV51701.2025.01785"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Controlnet++: improving conditional controls with efficient consistency feedback. In: ECCV, pp. 129\u2013147 (2024)","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"5_CR21","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. NeurIPS 36, 34892\u201334916 (2023)","journal-title":"NeurIPS"},{"issue":"2","key":"5_CR22","first-page":"147","volume":"6","author":"S Manchanda","year":"2024","unstructured":"Manchanda, S., et al.: D-LORD: DYSL-AI database for low-resolution disguised face recognition. T-BIOM 6(2), 147\u2013157 (2024)","journal-title":"T-BIOM"},{"key":"5_CR23","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML, pp. 16784\u201316804 (2022)"},{"key":"5_CR24","unstructured":"Pan, X., Dong, L., Huang, S., Peng, Z., Chen, W., Wei, F.: Kosmos-g: generating images in context with multimodal large language models. In: ICLR, pp. 40959\u201340974 (2024)"},{"key":"5_CR25","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: ICLR, pp. 1862\u20131874 (2024)"},{"key":"5_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"5_CR27","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"5_CR28","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821\u20138831 (2021)"},{"key":"5_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: CVPR, pp. 10674\u201310685 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR30","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS 35, 36479\u201336494 (2022)","journal-title":"NeurIPS"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Sheynin, S., et al.: Emu edit: precise image editing via recognition and generation tasks. In: CVPR, pp. 8871\u20138879 (2024)","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Singh, J., Zhang, J., Liu, Q., Smith, C., Lin, Z., Zheng, L.: Smartmask: context aware high-fidelity mask generation for fine-grained object insertion and layout control. In: CVPR, pp. 6497\u20136506 (2024)","DOI":"10.1109\/CVPR52733.2024.00621"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Xie, S., Zhang, Z., Lin, Z., Hinz, T., Zhang, K.: Smartbrush: text and shape guided object inpainting with diffusion model. In: CVPR, pp. 22428\u201322437 (2023)","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"5_CR34","first-page":"31428","volume":"36","author":"K Zhang","year":"2023","unstructured":"Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: Magicbrush: a manually annotated dataset for instruction-guided image editing. NeurIPS 36, 31428\u201331449 (2023)","journal-title":"NeurIPS"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Hive: harnessing human feedback for instructional visual editing. In: CVPR, pp. 9026\u20139036 (2024)","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"5_CR36","first-page":"3058","volume":"37","author":"H Zhao","year":"2024","unstructured":"Zhao, H., et al.: Ultraedit: instruction-based fine-grained image editing at scale. NeurIPS 37, 3058\u20133093 (2024)","journal-title":"NeurIPS"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37174-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:08:31Z","timestamp":1789715311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_5","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":"19 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}