{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:18:52Z","timestamp":1789121932513,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374349","type":"print"},{"value":"9783032374356","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\/978-3-032-37435-6_10","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:15:49Z","timestamp":1789118149000},"page":"172-189","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["D3F-IR: Dual-Domain Deterministic Flow Matching for\u00a0Visible-to-Infrared Translation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8999-8035","authenticated-orcid":false,"given":"Peiyi","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4235-5720","authenticated-orcid":false,"given":"Diedong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2804-1133","authenticated-orcid":false,"given":"Zhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4148-3331","authenticated-orcid":false,"given":"Zhenming","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4491-7967","authenticated-orcid":false,"given":"Bing","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3088-0016","authenticated-orcid":false,"given":"Shuaicheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"82410","DOI":"10.1109\/ACCESS.2023.3301119","volume":"11","author":"M Brenner","year":"2023","unstructured":"Brenner, M., Reyes, N.H., Susnjak, T., Barczak, A.L.: RGB-D and thermal sensor fusion: a systematic literature review. IEEE Access 11, 82410\u201382442 (2023)","journal-title":"IEEE Access"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10_CR3","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. arXiv preprint arXiv:2403.03206 (2024)"},{"key":"10_CR4","unstructured":"Feng, R., Yu, C., Deng, W., Hu, P., Wu, T.: On the guidance of flow matching. In: ICML (2025)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Geng, Z., Deng, M., Bai, X., Kolter, J.Z., He, K.: Mean flows for one-step generative modeling. In: NeurIPS (2025)","DOI":"10.52202\/085713-2534"},{"key":"10_CR6","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Han, Z., Zhang, S., Su, Y., Chen, X., Mei, S.: DR-AVIT: toward diverse and realistic aerial visible-to-infrared image translation. IEEE Trans. Geosci. Remote Sens. 62, 1\u201313 (2024)","DOI":"10.1109\/TGRS.2024.3405989"},{"key":"10_CR8","unstructured":"Haviv, D., Pooladian, A.A., Pe\u2019er, D., Amos, B.: Wasserstein flow matching: generative modeling over families of distributions. In: ICML (2025)"},{"key":"10_CR9","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"10_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., Kweon, I.S.: Multispectral pedestrian detection: Benchmark dataset and baselines. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"10_CR14","unstructured":"Kim, B., Kwon, G., Kim, K., Ye, J.C.: Unpaired image-to-image translation via neural schr\u00f6dinger bridge. In: ICLR (2024)"},{"key":"10_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-030-11024-6_46","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"VV Kniaz","year":"2019","unstructured":"Kniaz, V.V., Knyaz, V.A., Hlad\u016fvka, J., Kropatsch, W.G., Mizginov, V.: ThermalGAN: multimodal color-to-thermal image translation for person re-identification in multispectral dataset. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11134, pp. 606\u2013624. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11024-6_46"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Lee, D.G., Jeon, M.H., Cho, Y., Kim, A.: Edge-guided multi-domain RGB-to-TIR image translation for training vision tasks with challenging labels. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10161210"},{"issue":"20","key":"10_CR19","doi-asserted-by":"publisher","first-page":"3817","DOI":"10.3390\/rs16203817","volume":"16","author":"B Li","year":"2024","unstructured":"Li, B., Ma, D., He, F., Zhang, Z., Zhang, D., Li, S.: Infrared image generation based on visual state space and contrastive learning. Remote Sensing 16(20), 3817 (2024)","journal-title":"Remote Sensing"},{"key":"10_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977","volume":"96","author":"C Li","year":"2019","unstructured":"Li, C., Liang, X., Lu, Y., Zhao, N., Tang, J.: RGB-T object tracking: benchmark and baseline. Pattern Recogn. 96, 106977 (2019)","journal-title":"Pattern Recogn."},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Li, N., Wang, H., Zhao, H., Ou, W.: Cross-modal visible-to-infrared image translation in remote sensing guided by thermal features. IEEE Trans. Geosci. Remote Sens. 63, 1\u201316 (2025)","DOI":"10.1109\/TGRS.2025.3579267"},{"key":"10_CR22","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) ECCV. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Raw-flow: advancing RGB-to-raw image reconstruction with deterministic latent flow matching. In: AAAI (2026)","DOI":"10.1609\/aaai.v40i9.37682"},{"key":"10_CR26","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)"},{"issue":"2","key":"10_CR27","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1007\/s00371-023-02847-5","volume":"40","author":"D Ma","year":"2024","unstructured":"Ma, D., Xian, Y., Li, B., Li, S., Zhang, D.: Visible-to-infrared image translation based on an improved CGAN. Vis. Comput. 40(2), 1289\u20131298 (2024)","journal-title":"Vis. Comput."},{"key":"10_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111816","volume":"169","author":"F Mao","year":"2026","unstructured":"Mao, F., et al.: PID: physics-informed diffusion model for infrared image generation. Pattern Recogn. 169, 111816 (2026)","journal-title":"Pattern Recogn."},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"10_CR30","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.patrec.2022.01.026","volume":"155","author":"MA \u00d6zkano\u011flu","year":"2022","unstructured":"\u00d6zkano\u011flu, M.A., Ozer, S.: InfraGAN: a GAN architecture to transfer visible images to infrared domain. Pattern Recogn. Lett. 155, 69\u201376 (2022)","journal-title":"Pattern Recogn. Lett."},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Paranjape, J.N., de\u00a0Melo, C., Patel, V.M.: F-ViTA: foundation model guided visible to thermal translation. arXiv preprint arXiv:2504.02801 (2025)","DOI":"10.1109\/WACV61042.2026.00546"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Parmar, G., Zhang, R., Zhu, J.Y.: On buggy resizing libraries and surprising subtleties in fid calculation. arXiv preprint arXiv:2104.11222 (2021)","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Ran, L., Wang, L., Wang, G., Wang, P., Zhang, Y.: DiffV2IR: visible-to-infrared diffusion model via vision-language understanding. arXiv preprint arXiv:2503.19012 (2025)","DOI":"10.2139\/ssrn.6064478"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Shin, U., Lee, K., Kweon, I.S., Oh, J.: Complementary random masking for RGB-thermal semantic segmentation. In: ICRA (2024)","DOI":"10.1109\/ICRA57147.2024.10611200"},{"key":"10_CR37","unstructured":"Sim\u00e9oni, O., et\u00a0al.: DINOv3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"10_CR38","unstructured":"Teledyne FLIR: Teledyne FLIR ADAS thermal dataset. https:\/\/oem.flir.com\/solutions\/automotive\/adas-dataset-form\/. Accessed 03 Nov 2025"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Tuzcuo\u011flu, \u00d6., K\u00f6ksal, A., Sofu, B., Kalkan, S., Alatan, A.A.: XoFTR: cross-modal feature matching transformer. In: CVPR (2024)","DOI":"10.1109\/CVPRW63382.2024.00431"},{"key":"10_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"10_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2024.105314","volume":"139","author":"S Wang","year":"2024","unstructured":"Wang, S., Sun, G., Dong, L., Zheng, B.: PAS-GAN: a GAN based on the pyramid across-scale module for visible-infrared image transformation. Infrared Phys. Technol. 139, 105314 (2024)","journal-title":"Infrared Phys. Technol."},{"issue":"4","key":"10_CR42","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.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Wu, H., Li, X., Yang, S., Tan, H., Tang, Y., Liu, T.: UniiVFT: towards a unified framework for infrared-visible fusion and translation. In: ICASSP (2025)","DOI":"10.1109\/ICASSP49660.2025.10890253"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: StegoGAN: leveraging steganography for non-bijective image-to-image translation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00757"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Xiao, J., Nayak, R., Zhang, N., Tortei, D., Loianno, G.: ThermalGen: style-disentangled flow-based generative models for RGB-to-thermal image translation. In: NeurIPS (2025)","DOI":"10.52202\/085713-1112"},{"key":"10_CR46","unstructured":"Yang, L., et al.: Consistency flow matching: defining straight flows with velocity consistency. arXiv preprint arXiv:2407.02398 (2024)"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"10_CR48","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":"10_CR49","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. In: ICLR (2026)"},{"key":"10_CR50","unstructured":"Zhou, Z., Liu, W.: An error analysis of flow matching for deep generative modeling. In: ICML (2025)"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.244"}],"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\/978-3-032-37435-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:16:08Z","timestamp":1789118168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37435-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374349","9783032374356"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37435-6_10","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":"12 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"}}]}}