{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T23:22:45Z","timestamp":1761952965708,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533978","type":"print"},{"value":"9789819533985","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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\/978-981-95-3398-5_8","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T23:19:15Z","timestamp":1761952755000},"page":"89-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Art3D-Fusion: A Hybrid Framework for\u00a0Visual Synthesis with\u00a0Artistic Control"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5863-2288","authenticated-orcid":false,"given":"Kohou","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2430-6944","authenticated-orcid":false,"given":"Ping","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-0277","authenticated-orcid":false,"given":"Zhaoxiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2492-403X","authenticated-orcid":false,"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6796-6043","authenticated-orcid":false,"given":"Zezhou","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6697-3220","authenticated-orcid":false,"given":"Huan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1944-1530","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1171-0281","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-7049","authenticated-orcid":false,"given":"Shiguo","family":"Lian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: Optimizing for the shortest path in denoising diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.01679"},{"key":"8_CR2","unstructured":"Chowdhary, N., Chauhan, M., Bhura, P.: An efficient method of depth map generation and rendering to convert 2D video to 3D. Computer 24(8) (2024)"},{"key":"8_CR3","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"8_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103148","volume":"78","author":"P Gao","year":"2021","unstructured":"Gao, P., Zhu, T., Paul, M.: Disocclusion filling for depth-based view synthesis with adaptive utilization of temporal correlations. J. Vis. Commun. Image Represent. 78, 103148 (2021)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Gautier, J., Le\u00a0Meur, O., Guillemot, C.: Depth-based image completion for view synthesis. In: 2011 3DTV Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON), pp.\u00a01\u20134. IEEE (2011)","DOI":"10.1109\/3DTV.2011.5877193"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"8_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":"8_CR9","doi-asserted-by":"crossref","unstructured":"Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition, pp. 2366\u20132369. IEEE (2010)","DOI":"10.1109\/ICPR.2010.579"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking fid: Towards a better evaluation metric for image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9307\u20139315 (2024)","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9492\u20139502 (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"issue":"1","key":"8_CR12","doi-asserted-by":"publisher","first-page":"1219849","DOI":"10.1155\/2021\/1219849","volume":"2021","author":"R Kuang","year":"2021","unstructured":"Kuang, R.: Design and implementation of 3D film and television scene production algorithm based on the internet of things. Wirel. Commun. Mob. Comput. 2021(1), 1219849 (2021)","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"8_CR13","unstructured":"Owl3D: Owl3D: AI-powered 2D to 3D conversion software (2024). https:\/\/www.owl3d.com\/. Accessed 15 Nov 2024"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"8_CR15","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"8_CR16","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE TPAMI 44(3), 1623\u20131637 (2020)","journal-title":"IEEE TPAMI"},{"key":"8_CR17","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":"8_CR18","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"8_CR19","unstructured":"Saxena, S., Kar, A., Norouzi, M., Fleet, D.J.: Monocular depth estimation using diffusion models. arXiv preprint arXiv:2302.14816 (2023)"},{"issue":"6","key":"8_CR20","doi-asserted-by":"publisher","first-page":"8423","DOI":"10.1007\/s11042-020-10035-z","volume":"80","author":"DRIM Setiadi","year":"2021","unstructured":"Setiadi, D.R.I.M.: PSNR vs SSIM: imperceptibility quality assessment for image steganography. Multimedia Tools Appl. 80(6), 8423\u20138444 (2021)","journal-title":"Multimedia Tools Appl."},{"issue":"5","key":"8_CR21","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/JSTSP.2012.2204723","volume":"6","author":"M Solh","year":"2012","unstructured":"Solh, M., AlRegib, G.: Hierarchical hole-filling for depth-based view synthesis in FTV and 3D video. IEEE J. Sel. Top. Signal Process. 6(5), 495\u2013504 (2012)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: recurrent all-pairs field transforms for optical flow (extended abstract). In: International Joint Conference on Artificial Intelligence (2021)","DOI":"10.24963\/ijcai.2021\/662"},{"key":"8_CR23","doi-asserted-by":"publisher","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 842\u2013857. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_51","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"8_CR24","unstructured":"Yang, L., et al.: Depth anything v2. arXiv preprint arXiv:2406.09414 (2024)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Learning to recover 3D scene shape from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 204\u2013213 (2021)","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5729\u20135739 (2023)","DOI":"10.1109\/ICCV51070.2023.00527"},{"issue":"1","key":"8_CR28","first-page":"8562323","volume":"2020","author":"K Zhou","year":"2020","unstructured":"Zhou, K., Meng, X., Cheng, B.: Review of stereo matching algorithms based on deep learning. Comput. Intell. Neurosci. 2020(1), 8562323 (2020)","journal-title":"Comput. Intell. Neurosci."}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3398-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T23:19:19Z","timestamp":1761952759000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3398-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819533978","9789819533985"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3398-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}