{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T20:14:33Z","timestamp":1785269673214,"version":"3.55.0"},"publisher-location":"Cham","reference-count":81,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726323","type":"print"},{"value":"9783031726330","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72633-0_8","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T07:54:33Z","timestamp":1732175673000},"page":"134-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["IDOL: Unified Dual-Modal Latent Diffusion for\u00a0Human-Centric Joint Video-Depth Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3277-3329","authenticated-orcid":false,"given":"Yuanhao","family":"Zhai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-1336","authenticated-orcid":false,"given":"Kevin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0867-8863","authenticated-orcid":false,"given":"Linjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6507-3657","authenticated-orcid":false,"given":"Chung-Ching","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3156-4429","authenticated-orcid":false,"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5808-0889","authenticated-orcid":false,"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1639-4561","authenticated-orcid":false,"given":"David","family":"Doermann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7901-8793","authenticated-orcid":false,"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5894-7828","authenticated-orcid":false,"given":"Zicheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5705-876X","authenticated-orcid":false,"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"8_CR1","unstructured":"Amit, T., Shaharbany, T., Nachmani, E., Wolf, L.: Segdiff: image segmentation with diffusion probabilistic models. arXiv preprint arXiv:2112.00390 (2021)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Atapour-Abarghouei, A., Breckon, T.P.: Real-time monocular depth estimation using synthetic data with domain adaptation via image style transfer. In: CVPR, pp. 2800\u20132810 (2018)","DOI":"10.1109\/CVPR.2018.00296"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Bae, J., Moon, S., Im, S.: Deep digging into the generalization of self-supervised monocular depth estimation. In: AAAI, vol.\u00a037, pp. 187\u2013196 (2023)","DOI":"10.1609\/aaai.v37i1.25090"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Balaji, Y., Min, M.R., Bai, B., Chellappa, R., Graf, H.P.: Conditional GAN with discriminative filter generation for text-to-video synthesis. In: IJCAI, vol.\u00a01, p.\u00a02 (2019)","DOI":"10.24963\/ijcai.2019\/276"},{"key":"8_CR5","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126 (2021)"},{"key":"8_CR6","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"8_CR8","unstructured":"Chang, D., et al.: Magicdance: realistic human dance video generation with motions & facial expressions transfer. arXiv preprint arXiv:2311.12052 (2023)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: diffusion model for object detection. In: ICCV, pp. 19830\u201319843 (2023)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Chen, T., Li, L., Saxena, S., Hinton, G., Fleet, D.J.: A generalist framework for panoptic segmentation of images and videos. In: ICCV, pp. 909\u2013919 (2023)","DOI":"10.1109\/ICCV51070.2023.00090"},{"key":"8_CR11","unstructured":"Chen, W., et al.: Control-a-video: Controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"8_CR12","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: ICCV, pp. 7346\u20137356 (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: StyleGAN-human: a data-centric odyssey of human generation. In: ECCV, pp. 1\u201319 (2022)","DOI":"10.1007\/978-3-031-19787-1_1"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zhang, R., Wang, X., Tang, X., Luo, P.: DeepFashion2: a versatile benchmark for detection, pose estimation, segmentation and re-identification of clothing images. In: CVPR, pp. 5337\u20135345 (2019)","DOI":"10.1109\/CVPR.2019.00548"},{"key":"8_CR16","unstructured":"Geyer, M., Bar-Tal, O., Bagon, S., Dekel, T.: TokenFlow: consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373 (2023)"},{"issue":"11","key":"8_CR17","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"8_CR18","unstructured":"Gu, J., et al.: Nerfdiff: single-image view synthesis with nerf-guided distillation from 3D-aware diffusion, pp. 11808\u201311826 (2023)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: CVPR, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"8_CR20","unstructured":"Guo, Y., et al.: Animatediff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Ha, S., Kersner, M., Kim, B., Seo, S., Kim, D.: Marionette: few-shot face reenactment preserving identity of unseen targets. In: AAAI, vol.\u00a034, pp. 10893\u201310900 (2020)","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"8_CR22","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":"8_CR23","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, vol. 30 (2017)"},{"key":"8_CR24","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"8_CR25","unstructured":"Hu, L., Gao, X., Zhang, P., Sun, K., Zhang, B., Bo, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2023)"},{"key":"8_CR26","unstructured":"Hu, Z., Xu, D.: Videocontrolnet: a motion-guided video-to-video translation framework by using diffusion model with controlnet. arXiv preprint arXiv:2307.14073 (2023)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Jafarian, Y., Park, H.S.: Learning high fidelity depths of dressed humans by watching social media dance videos. In: CVPR, pp. 12753\u201312762 (2021)","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DDP: diffusion model for dense visual prediction. arXiv preprint arXiv:2303.17559 (2023)","DOI":"10.1109\/ICCV51070.2023.01987"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Ju, X., Zeng, A., Zhao, C., Wang, J., Zhang, L., Xu, Q.: HumanSD: a native skeleton-guided diffusion model for human image generation. arXiv preprint arXiv:2304.04269 (2023)","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.C., Kemelmacher-Shlizerman, I.: Dreampose: fashion image-to-video synthesis via stable diffusion. arXiv preprint arXiv:2304.06025 (2023)","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"8_CR32","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: CVPR, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"10","key":"8_CR36","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+ D 120: a large-scale benchmark for 3D human activity understanding. IEEE TPAMI 42(10), 2684\u20132701 (2019)","journal-title":"IEEE TPAMI"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"8_CR38","unstructured":"Liu, X., et al.: Hyperhuman: hyper-realistic human generation with latent structural diffusion. arXiv preprint arXiv:2310.08579 (2023)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Luan, T., et al.: Spectrum AUC difference (SAUCD): human-aligned 3D shape evaluation. In: CVPR, pp. 20155\u201320164 (2024)","DOI":"10.1109\/CVPR52733.2024.01905"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Luan, T., Wang, Y., Zhang, J., Wang, Z., Zhou, Z., Qiao, Y.: PC-HMR: pose calibration for 3D human mesh recovery from 2d images\/videos. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i3.16326"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Luan, T., et al.: High fidelity 3D hand shape reconstruction via scalable graph frequency decomposition. In: CVPR, pp. 16795\u201316804 (2023)","DOI":"10.1109\/CVPR52729.2023.01611"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Follow your pose: pose-guided text-to-video generation using pose-free videos. arXiv preprint arXiv:2304.01186 (2023)","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"8_CR43","unstructured":"Mallya, A., Wang, T.C., Liu, M.Y.: Implicit warping for animation with image sets. In: NeurIPS, vol. 35, pp. 22438\u201322450 (2022)"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: CVPR, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"8_CR45","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. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"8_CR46","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-E: a system for generating 3D point clouds from complex prompts. arXiv preprint arXiv:2212.08751 (2022)"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGAN: subject agnostic face swapping and reenactment. In: ICCV, pp. 7184\u20137193 (2019)","DOI":"10.1109\/ICCV.2019.00728"},{"key":"8_CR48","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Qi, C., et al.: Fatezero: fusing attentions for zero-shot text-based video editing. arXiv preprint arXiv:2303.09535 (2023)","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Qian, S., et al.: Make a face: towards arbitrary high fidelity face manipulation. In: ICCV, pp. 10033\u201310042 (2019)","DOI":"10.1109\/ICCV.2019.01013"},{"key":"8_CR51","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision, pp. 8748\u20138763 (2021)"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Raj, A., et\u00a0al.: Dreambooth3D: subject-driven text-to-3D generation. arXiv preprint arXiv:2303.13508 (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"8_CR54","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_CR55","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1007\/978-3-031-20071-7_15","volume-title":"ECCV 2022","author":"F Reda","year":"2022","unstructured":"Reda, F., Kontkanen, J., Tabellion, E., Sun, D., Pantofaru, C., Curless, B.: FILM: frame interpolation for large motion. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13667, pp. 250\u2013266. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_15"},{"key":"8_CR56","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. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Ruan, L., et al.: MM-diffusion: learning multi-modal diffusion models for joint audio and video generation. In: CVPR, pp. 10219\u201310228 (2023)","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"8_CR59","unstructured":"Saxena, S., Kar, A., Norouzi, M., Fleet, D.J.: Monocular depth estimation using diffusion models. arXiv preprint arXiv:2302.14816 (2023)"},{"key":"8_CR60","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"8_CR61","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: CVPR, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"8_CR62","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"8_CR64","unstructured":"Stan, G.B.M., et\u00a0al.: LDM3D: latent diffusion model for 3D. arXiv preprint arXiv:2305.10853 (2023)"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"Tang, H., Wang, W., Xu, D., Yan, Y., Sebe, N.: GestureGAN for hand gesture-to-gesture translation in the wild. In: ACM MM, pp. 774\u2013782 (2018)","DOI":"10.1145\/3240508.3240704"},{"key":"8_CR66","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: CVPR, pp. 1921\u20131930 (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"8_CR67","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Disco: disentangled control for referring human dance generation in real world. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"8_CR69","unstructured":"Watson, D., Chan, W., Martin-Brualla, R., Ho, J., Tagliasacchi, A., Norouzi, M.: Novel view synthesis with diffusion models. arXiv preprint arXiv:2210.04628 (2022)"},{"key":"8_CR70","doi-asserted-by":"crossref","unstructured":"Wiles, O., Koepke, A., Zisserman, A.: X2Face: a network for controlling face generation using images, audio, and pose codes. In: ECCV, pp. 670\u2013686 (2018)","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"8_CR71","unstructured":"Wolleb, J., Sandk\u00fchler, R., Bieder, F., Valmaggia, P., Cattin, P.C.: Diffusion models for implicit image segmentation ensembles. In: International Conference on Medical Imaging with Deep Learning, pp. 1336\u20131348. PMLR (2022)"},{"key":"8_CR72","unstructured":"Wu, J., Fang, H., Zhang, Y., Yang, Y., Xu, Y.: Medsegdiff: medical image segmentation with diffusion probabilistic model. arXiv preprint arXiv:2211.00611 (2022)"},{"key":"8_CR73","doi-asserted-by":"crossref","unstructured":"Wynn, J., Turmukhambetov, D.: Diffusionerf: regularizing neural radiance fields with denoising diffusion models. In: CVPR, pp. 4180\u20134189 (2023)","DOI":"10.1109\/CVPR52729.2023.00407"},{"key":"8_CR74","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Magicanimate: temporally consistent human image animation using diffusion model. arXiv preprint arXiv:2311.16498 (2023)","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"8_CR75","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"8_CR76","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zeng, A., Yuan, C., Li, Y.: Effective whole-body pose estimation with two-stages distillation. In: ICCV, pp. 4210\u20134220 (2023)","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"8_CR77","doi-asserted-by":"crossref","unstructured":"Zakharov, E., Shysheya, A., Burkov, E., Lempitsky, V.: Few-shot adversarial learning of realistic neural talking head models. In: ICCV, pp. 9459\u20139468 (2019)","DOI":"10.1109\/ICCV.2019.00955"},{"key":"8_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"8_CR79","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhang, H.: Thin-plate spline motion model for image animation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"8_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, S., Fu, H., Gong, M., Tao, D.: Geometry-aware symmetric domain adaptation for monocular depth estimation. In: CVPR, pp. 9788\u20139798 (2019)","DOI":"10.1109\/CVPR.2019.01002"},{"key":"8_CR81","doi-asserted-by":"crossref","unstructured":"Zheng, C., Cham, T.J., Cai, J.: T2Net: synthetic-to-realistic translation for solving single-image depth estimation tasks. In: ECCV, pp. 767\u2013783 (2018)","DOI":"10.1007\/978-3-030-01234-2_47"}],"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\/978-3-031-72633-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T18:46:51Z","timestamp":1733078811000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72633-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726323","9783031726330"],"references-count":81,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72633-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 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"}}]}}