{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:27:31Z","timestamp":1780392451373,"version":"3.54.1"},"publisher-location":"Cham","reference-count":96,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729829","type":"print"},{"value":"9783031729836","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72983-6_23","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"400-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Beyond the\u00a0Contact: Discovering Comprehensive Affordance for\u00a03D Objects from\u00a0Pre-trained 2D Diffusion Models"],"prefix":"10.1007","author":[{"given":"Hyeonwoo","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sookwan","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanbyul","family":"Joo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Bahl, S., Mendonca, R., Chen, L., Jain, U., Pathak, D.: Affordances from human videos as a versatile representation for robotics. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B.L., Xie, X., Petrov, I., Sminchisescu, C., Theobalt, C., Pons-Moll, G.: BEHAVE: dataset and method for tracking human object interactions. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Ham, C., Kemp, C.C., Hays, J.: ContactDB: analyzing and predicting grasp contact via thermal imaging. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00891"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Handa, A., Hays, J., Fox, D.: ContactGrasp: functional multi-finger grasp synthesis from contact. In: IROS (2019)","DOI":"10.1109\/IROS40897.2019.8967960"},{"key":"23_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/978-3-030-58601-0_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Brahmbhatt","year":"2020","unstructured":"Brahmbhatt, S., Tang, C., Twigg, C.D., Kemp, C.C., Hays, J.: ContactPose: a dataset of grasps with object contact and hand pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 361\u2013378. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_22"},{"key":"23_CR6","unstructured":"Cai, M., Kitani, K.M., Sato, Y.: Understanding hand-object manipulation with grasp types and object attributes. In: RSS (2016)"},{"key":"23_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-58452-8_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Cao","year":"2020","unstructured":"Cao, Z., Gao, H., Mangalam, K., Cai, Q.-Z., Vo, M., Malik, J.: Long-term human motion prediction with scene context. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_23"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Chai, L., Zhu, J.Y., Shechtman, E., Isola, P., Zhang, R.: Ensembling with deep generative views. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01475"},{"key":"23_CR9","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. Technical report. arXiv:1512.03012 (2015)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Huang, S., Yuan, T., Qi, S., Zhu, Y., Zhu, S.C.: Holistic++ scene understanding: single-view 3D holistic scene parsing and human pose estimation with human-object interaction and physical commonsense. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00874"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE TPAMI (2002)","DOI":"10.1109\/34.1000236"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Deng, S., Xu, X., Wu, C., Chen, K., Jia, K.: 3D AffordanceNet: a benchmark for visual object affordance understanding. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Three-dimensional reconstruction of human interactions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. In: CACM (1981)","DOI":"10.1145\/358669.358692"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Gao, W., Tedrake, R.: kPAM-SC: generalizable manipulation planning using keypoint affordance and shape completion. In: ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9561428"},{"key":"23_CR16","unstructured":"Garg, M., Garg, P., Vohra, R.: Advanced Fibonacci sequence with golden ratio. IJSER (2014)"},{"key":"23_CR17","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception. Houghton Mifflin (1979)"},{"key":"23_CR18","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Grady, P., Tang, C., Twigg, C.D., Vo, M., Brahmbhatt, S., Kemp, C.C.: ContactOpt: optimizing contact to improve grasps. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Han, S., Joo, H.: Learning canonicalized 3D human-object spatial relations from unbounded synthesized images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01451"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Hao, Z., Mallya, A., Belongie, S., Liu, M.Y.: GANcraft: unsupervised 3D neural rendering of Minecraft worlds. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01381"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3D human pose ambiguities with 3D scene constraints. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00237"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3D scenes by learning human-scene interaction. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"23_CR24","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? arXiv:2210.07574 (2022)"},{"key":"23_CR25","unstructured":"Hermans, T., Rehg, J.M., Bobick, A.: Affordance prediction via learned object attributes. In: ICRA (2011)"},{"key":"23_CR26","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv:2208.01626 (2022)"},{"key":"23_CR27","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Huang, C.H.P., et al.: Capturing and inferring dense full-body human-scene contact. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Huang, Y., Taheri, O., Black, M.J., Tzionas, D.: InterCap: joint markerless 3D tracking of humans and objects in interaction from multi-view RGB-D images. In: IJCV (2024)","DOI":"10.1007\/s11263-024-01984-1"},{"key":"23_CR30","unstructured":"Jahanian, A., Puig, X., Tian, Y., Isola, P.: Generative models as a data source for multiview representation learning. arXiv:2106.05258 (2021)"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Jian, J., Liu, X., Li, M., Hu, R., Liu, J.: AffordPose: a large-scale dataset of hand-object interactions with affordance-driven hand pose. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01352"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, W., Kolotouros, N., Pavlakos, G., Zhou, X., Daniilidis, K.: Coherent reconstruction of multiple humans from a single image. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: NeuralHOFusion: neural volumetric rendering under human-object interactions. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00606"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Kulal, S., et al.: Putting people in their place: affordance-aware human insertion into scenes. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01639"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Grauman, K.: Predicting important objects for egocentric video summarization. IJCV (2015)","DOI":"10.1007\/s11263-014-0794-5"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Levine, S., Shah, D.: Learning robotic navigation from experience: principles, methods and recent results. Philos. Trans. R. Soc. B (2022)","DOI":"10.1098\/rstb.2021.0447"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Li, G., Jampani, V., Sun, D., Sevilla-Lara, L.: Locate: localize and transfer object parts for weakly supervised affordance grounding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Li, L., Dai, A.: GenZI: zero-shot 3D human-scene interaction generation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01934"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Li, Z., Sedlar, J., Carpentier, J., Laptev, I., Mansard, N., Sivic, J.: Estimating 3D motion and forces of person-object interactions from monocular video. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00884"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. In: Proceedings ACM SIGGRAPH Asia (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"23_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1007\/978-3-030-58542-6_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Lou","year":"2020","unstructured":"Lou, Y., et al.: Human correspondence consensus for 3D object semantic understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 496\u2013512. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_30"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: RePaint: inpainting using denoising diffusion probabilistic models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Mao, C., Cha, A., Gupta, A., Wang, H., Yang, J., Vondrick, C.: Generative interventions for causal learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00394"},{"key":"23_CR48","unstructured":"McCool, M., Fiume, E.: Hierarchical Poisson disk sampling distributions. In: Graphics Interface (1992)"},{"key":"23_CR49","unstructured":"Melas-Kyriazi, L., Rupprecht, C., Laina, I., Vedaldi, A.: Finding an unsupervised image segmenter in each of your deep generative models. arXiv:2105.08127 (2021)"},{"key":"23_CR50","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Mihajlovic, M., Saito, S., Bansal, A., Zollhoefer, M., Tang, S.: COAP: compositional articulated occupancy of people. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01285"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Mo, K., et al.: PartNet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00100"},{"key":"23_CR53","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 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Monszpart, A., Guerrero, P., Ceylan, D., Yumer, E., Mitra, N.J.: iMapper: interaction-guided scene mapping from monocular videos. ACM TOG (2019)","DOI":"10.1145\/3306346.3322961"},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Lee, K.M.: Accurate 3D hand pose estimation for whole-body 3D human mesh estimation. In: CVPRW (2022)","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"23_CR56","unstructured":"Nagarajan, T., Grauman, K.: Learning affordance landscapes for interaction exploration in 3D environments. In: NeurIPS (2020)"},{"key":"23_CR57","unstructured":"Oleynikova, H., Millane, A., Taylor, Z., Galceran, E., Nieto, J., Siegwart, R.: Signed distance fields: a natural representation for both mapping and planning. In: RSS Workshop (2016)"},{"key":"23_CR58","unstructured":"OpenAI: ChatGPT: optimizing language models for dialogue (2023). https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"23_CR59","unstructured":"OpenAI: GPT-4V(ision) system card (2023). https:\/\/openai.com\/research\/gpt-4v-system-card"},{"key":"23_CR60","unstructured":"Pan, X., Dai, B., Liu, Z., Loy, C.C., Luo, P.: Do 2D GANs know 3D shape? Unsupervised 3D shape reconstruction from 2D image GANs. arXiv:2011.00844 (2020)"},{"key":"23_CR61","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"23_CR62","doi-asserted-by":"crossref","unstructured":"Peebles, W., Zhu, J.Y., Zhang, R., Torralba, A., Efros, A.A., Shechtman, E.: GAN-supervised dense visual alignment. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01311"},{"key":"23_CR63","doi-asserted-by":"crossref","unstructured":"Petrov, I.A., Marin, R., Chibane, J., Pons-Moll, G.: Object pop-up: can we infer 3D objects and their poses from human interactions alone? In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00458"},{"key":"23_CR64","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv:2204.06125 (2022)"},{"key":"23_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-58558-7_5","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Rempe","year":"2020","unstructured":"Rempe, D., Guibas, L.J., Hertzmann, A., Russell, B., Villegas, R., Yang, J.: Contact and human dynamics from monocular video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 71\u201387. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_5"},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: TEXTure: text-guided texturing of 3D shapes. In: Proceedings ACM SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"23_CR67","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 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR68","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. In: Proceedings ACM SIGGRAPH Asia (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"23_CR69","doi-asserted-by":"crossref","unstructured":"Savva, M., Chang, A.X., Hanrahan, P., Fisher, M., Nie\u00dfner, M.: PiGraphs: learning interaction snapshots from observations. ACM TOG (2016)","DOI":"10.1145\/2992138.2992147"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Shannon, C.E.: A Mathematical Theory of Communication. ACM SIGMOBILE (2001)","DOI":"10.1145\/584091.584093"},{"key":"23_CR71","unstructured":"Sketchfab: Sketchfab (2023). https:\/\/sketchfab.com\/"},{"key":"23_CR72","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"23_CR73","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv:2010.02502 (2020)"},{"key":"23_CR74","doi-asserted-by":"crossref","unstructured":"Sun, G., et al.: Neural free-viewpoint performance rendering under complex human-object interactions. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475442"},{"key":"23_CR75","doi-asserted-by":"crossref","unstructured":"Swain, M.J., Ballard, D.H.: Color indexing. IJCV (1991)","DOI":"10.1007\/BF00130487"},{"key":"23_CR76","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-58548-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Taheri","year":"2020","unstructured":"Taheri, O., Ghorbani, N., Black, M.J., Tzionas, D.: GRAB: a dataset of whole-body human grasping of objects. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 581\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_34"},{"key":"23_CR77","unstructured":"Tanaka, F.H.K.D.S., Aranha, C.: Data augmentation using GANs. arXiv:1904.09135 (2019)"},{"key":"23_CR78","unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. arXiv:2302.07944 (2023)"},{"key":"23_CR79","doi-asserted-by":"crossref","unstructured":"Tripathi, S., Chatterjee, A., Passy, J.C., Yi, H., Tzionas, D., Black, M.J.: DECO: dense estimation of 3D human-scene contact in the wild. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00735"},{"key":"23_CR80","doi-asserted-by":"crossref","unstructured":"Tritrong, N., Rewatbowornwong, P., Suwajanakorn, S.: Repurposing GANs for one-shot semantic part segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00445"},{"key":"23_CR81","doi-asserted-by":"crossref","unstructured":"Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. (2005)","DOI":"10.3354\/cr030079"},{"key":"23_CR82","unstructured":"Wu, W., et al.: DatasetDM: synthesizing data with perception annotations using diffusion models. In: NeurIPS (2023)"},{"key":"23_CR83","doi-asserted-by":"crossref","unstructured":"Xiang, F., et al.: SAPIEN: a simulated part-based interactive environment. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"23_CR84","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhu, S., Guo, H., Wu, S.: Automated labeling for robotic autonomous navigation through multi-sensory semi-supervised learning on big data. IEEE TBD (2021)","DOI":"10.1109\/TBDATA.2019.2892462"},{"key":"23_CR85","doi-asserted-by":"crossref","unstructured":"Xu, S., Li, Z., Wang, Y.X., Gui, L.Y.: InterDiff: generating 3D human-object interactions with physics-informed diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"23_CR86","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhan, X., Li, K., Xu, W., Li, J., Lu, C.: CPF: learning a contact potential field to model the hand-object interaction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01091"},{"key":"23_CR87","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Luo, J., Zha, Z.J.: Grounding 3D object affordance from 2D interactions in images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"23_CR88","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Zha, Z.J.: LEMON: learning 3D human-object interaction relation from 2D images. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01541"},{"key":"23_CR89","doi-asserted-by":"crossref","unstructured":"Ye, Y., et al.: Affordance diffusion: synthesizing hand-object interactions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02153"},{"key":"23_CR90","doi-asserted-by":"crossref","unstructured":"Yi, H., et al.: Human-aware object placement for visual environment reconstruction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00393"},{"key":"23_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Y., Ma, Q., Black, M.J., Tang, S.: PLACE: proximity learning of articulation and contact in 3D environments. In: 3DV (2020)","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"23_CR92","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1007\/978-3-031-20065-6_30","volume-title":"ECCV 2022","author":"X Zhang","year":"2022","unstructured":"Zhang, X., Bhatnagar, B.L., Starke, S., Guzov, V., Pons-Moll, G.: COUCH: towards controllable human-chair interactions. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13665, pp. 518\u2013535. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_30"},{"key":"23_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hassan, M., Neumann, H., Black, M.J., Tang, S.: Generating 3D people in scenes without people. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"23_CR94","unstructured":"Zhang, Y., et al.: Image GANs meet differentiable rendering for inverse graphics and interpretable 3D neural rendering. In: ICLR (2021)"},{"key":"23_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: DatasetGAN: efficient labeled data factory with minimal human effort. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"23_CR96","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20062-5_1","volume-title":"ECCV 2022","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Bhatnagar, B.L., Lenssen, J.E., Pons-Moll, G.: TOCH: spatio-temporal object correspondence to hand for motion refinement. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13663, pp. 1\u201319. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_1"}],"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\/978-3-031-72983-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:37:06Z","timestamp":1732963026000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72983-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031729829","9783031729836"],"references-count":96,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72983-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 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"}}]}}