{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T04:11:38Z","timestamp":1744949498682,"version":"3.40.4"},"reference-count":87,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006502","name":"Defense Sciences Office, DARPA","doi-asserted-by":"publisher","award":["HR00112290073"],"award-info":[{"award-number":["HR00112290073"]}],"id":[{"id":"10.13039\/100006502","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02270-w","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T07:42:26Z","timestamp":1734680546000},"page":"2967-2995","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2546-8190","authenticated-orcid":false,"given":"Utkarsh","family":"Nath","sequence":"first","affiliation":[]},{"given":"Rajhans","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Ankita","family":"Shukla","sequence":"additional","affiliation":[]},{"given":"Kuldeep","family":"Kulkarni","sequence":"additional","affiliation":[]},{"given":"Pavan","family":"Turaga","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,20]]},"reference":[{"issue":"6","key":"2270_CR1","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1109\/TPAMI.2008.37","volume":"30","author":"N Alajlan","year":"2008","unstructured":"Alajlan, N., Kamel, M. S., & Freeman, G. H. (2008). Geometry-based image retrieval in binary image databases. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(6), 1003\u20131013.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2270_CR2","doi-asserted-by":"crossref","unstructured":"Anokhin, I., Demochkin, K., Khakhulin, T., Sterkin, G., Lempitsky, V., & Korzhenkov, D. (2021). Image generators with conditionally-independent pixel synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 14278\u201314287.","DOI":"10.1109\/CVPR46437.2021.01405"},{"key":"2270_CR3","unstructured":"Arakawa, S., Tsunashima, H., Horita, D., Tanaka, K., & Morishima, S. (2023). Memory efficient diffusion probabilistic models via patch-based generation. arXiv preprint arXiv:2304.07087."},{"key":"2270_CR4","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In: International conference on machine learning (ICML), pp. 214\u2013223."},{"key":"2270_CR5","doi-asserted-by":"crossref","unstructured":"Barron, J., Mildenhall, B., Verbin, D., Srinivasan, P., & Hedman, P. (2022). Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5470\u20135479.","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"2270_CR6","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2018). Large scale GAN training for high fidelity natural image synthesis. In: International conference on learning representations (ICLR)."},{"key":"2270_CR7","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Lin, C.Z., Chan, M.A., Nagano, K., Pan, B., De\u00a0Mello, S., Gallo, O., Guibas, L.J., Tremblay, J., & Khamis, S., et\u00a0al. (2022). Efficient geometry-aware 3d generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 16123\u201316133.","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2270_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., & Zhang, H. (2019). Learning implicit fields for generative shape modeling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5939\u20135948.","DOI":"10.1109\/CVPR.2019.00609"},{"key":"2270_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., & Wang, X. (2021). Learning continuous image representation with local implicit image function. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 8628\u20138638.","DOI":"10.1109\/CVPR46437.2021.00852"},{"issue":"1","key":"2270_CR10","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.patcog.2003.06.003","volume":"37","author":"C-W Chong","year":"2004","unstructured":"Chong, C.-W., Raveendran, P., & Mukundan, R. (2004). Translation and scale invariants of Legendre moments. Pattern Recognition, 37(1), 119\u2013129.","journal-title":"Pattern Recognition"},{"issue":"8","key":"2270_CR11","first-page":"4021","volume":"44","author":"GG Chrysos","year":"2022","unstructured":"Chrysos, G. G., Moschoglou, S., Bouritsas, G., Deng, J., Panagakis, Y., & Zafeiriou, S. (2022). Deep polynomial neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(8), 4021\u20134034.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2270_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition (CVPR), pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2270_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). ArcFace: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 4690\u20134699.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"2270_CR14","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., & Nichol, A. (2021). Diffusion models beat Gans on image synthesis. Advances in Neural Information Processing Systems (NeurIPS), 34, 8780\u20138794.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR15","unstructured":"Ding, Z., Zhang, M., Wu, J., & Tu, Z. (2023). Patched denoising diffusion models for high-resolution image synthesis. In: The twelfth international conference on learning representations (ICLR)."},{"key":"2270_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S., et\u00a0al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In: International conference on learning representations (ICLR)."},{"key":"2270_CR17","first-page":"8320","volume":"34","author":"Y Du","year":"2021","unstructured":"Du, Y., Collins, K., Tenenbaum, J., & Sitzmann, V. (2021). Learning signal-agnostic manifolds of neural fields. Advances in Neural Information Processing Systems (NeurIPS), 34, 8320\u20138331.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR18","unstructured":"Dupont, E., Kim, H., Eslami, S., Rezende, D., & Rosenbaum, D. (2022a). From data to functa: Your data point is a function and you can treat it like one. In: International conference on machine learning (ICML)."},{"key":"2270_CR19","unstructured":"Dupont, E., Teh, Y. W., & Doucet, A. (2022b). Generative models as distributions of functions. In: International conference on artificial intelligence and statistics (AISTATS)."},{"issue":"10","key":"2270_CR20","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TPAMI.2003.1233902","volume":"25","author":"A Elad","year":"2003","unstructured":"Elad, A., & Kimmel, R. (2003). On bending invariant signatures for surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(10), 1285\u20131295.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"2270_CR21","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1109\/TPAMI.2003.1177154","volume":"25","author":"J Flusser","year":"2003","unstructured":"Flusser, J., Boldys, J., & Zitov\u00e1, B. (2003). Moment forms invariant to rotation and blur in arbitrary number of dimensions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2), 234\u2013246.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"2270_CR22","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/0031-3203(93)90098-H","volume":"26","author":"J Flusser","year":"1993","unstructured":"Flusser, J., & Suk, T. (1993). Pattern recognition by affine moment invariants. Pattern Recognition, 26(1), 167\u2013174.","journal-title":"Pattern Recognition"},{"issue":"8","key":"2270_CR23","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1109\/TPAMI.2006.154","volume":"28","author":"A Foulonneau","year":"2006","unstructured":"Foulonneau, A., Charbonnier, P., & Heitz, F. (2006). Affine-invariant geometric shape priors for region-based active contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(8), 1352\u20131357.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2270_CR24","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, P., Cheng, M.-M., & Yan, S. (2023). Mdtv2: Masked diffusion transformer is a strong image synthesizer. arXiv preprint arXiv:2303.14389.","DOI":"10.1109\/ICCV51070.2023.02117"},{"issue":"11","key":"2270_CR25","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139\u2013144.","journal-title":"Communications of the ACM"},{"key":"2270_CR26","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of wasserstein gans. Advances in Neural Information Processing Systems (NeurIPS), vol. 30."},{"key":"2270_CR27","first-page":"9841","volume":"33","author":"E H\u00e4rk\u00f6nen","year":"2020","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., & Paris, S. (2020). Ganspace: Discovering interpretable Gan controls. Advances in Neural Information Processing Systems (NeurIPS), 33, 9841\u20139850.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR28","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local Nash equilibrium. Advances in neural information processing systems 30."},{"key":"2270_CR29","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR30","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D. J., Norouzi, M., & Salimans, T. (2022). Cascaded diffusion models for high fidelity image generation. Journal of Machine Learning Research, 23, 1\u201347.","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"2270_CR31","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1109\/TIT.1962.1057692","volume":"8","author":"M-K Hu","year":"1962","unstructured":"Hu, M.-K. (1962). Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, 8(2), 179\u2013187.","journal-title":"IRE Transactions on Information Theory"},{"key":"2270_CR32","doi-asserted-by":"crossref","unstructured":"Joseph-Rivlin, M., Zvirin, A., & Kimmel, R. (2019). Momen(e)t: Flavor the moments in learning to classify shapes. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops.","DOI":"10.1109\/ICCVW.2019.00503"},{"key":"2270_CR33","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2270_CR34","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020). Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"2270_CR35","first-page":"852","volume":"34","author":"T Karras","year":"2021","unstructured":"Karras, T., Aittala, M., Laine, S., H\u00e4rk\u00f6nen, E., Hellsten, J., Lehtinen, J., & Aila, T. (2021). Alias-free generative adversarial networks. Advances in Neural Information Processing Systems (NeurIPS), 34, 852\u2013863.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"issue":"5","key":"2270_CR36","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1109\/34.55109","volume":"12","author":"A Khotanzad","year":"1990","unstructured":"Khotanzad, A., & Hong, Y. H. (1990). Invariant image recognition by Zernike moments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(5), 489\u2013497.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"8","key":"2270_CR37","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1109\/TCSVT.2003.815955","volume":"13","author":"HS Kim","year":"2003","unstructured":"Kim, H. S., & Lee, H.-K. (2003). Invariant image watermark using Zernike moments. IEEE Transactions on Circuits and Systems for Video Technology, 13(8), 766\u2013775.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2270_CR38","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., & Aila, T. (2019). Improved precision and recall metric for assessing generative models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 32."},{"key":"2270_CR39","unstructured":"Lee, K., Chang, H., Jiang, L., Zhang, H., Tu, Z., & Liu, C. (2021). Vitgan: Training gans with vision transformers. In: International conference on learning representations (ICLR)."},{"key":"2270_CR40","doi-asserted-by":"publisher","first-page":"124989","DOI":"10.1109\/ACCESS.2020.3007630","volume":"8","author":"D Li","year":"2020","unstructured":"Li, D., Shen, X., Yu, Y., Guan, H., Wang, H., & Li, D. (2020). GGM-net: Graph geometric moments convolution neural network for point cloud shape classification. IEEE Access, 8, 124989\u2013124998.","journal-title":"IEEE Access"},{"key":"2270_CR41","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.patrec.2017.05.011","volume":"105","author":"L Luciano","year":"2018","unstructured":"Luciano, L., & Hamza, A. B. (2018). Deep learning with geodesic moments for 3D shape classification. Pattern Recognition Letters, 105, 182\u2013190.","journal-title":"Pattern Recognition Letters"},{"key":"2270_CR42","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M. S., Barron, J. T., Dosovitskiy, A., & Duckworth, D. (2021). Nerf in the wild: Neural radiance fields for unconstrained photo collections. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 7210\u20137219.","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"1","key":"2270_CR43","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2021). Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1), 99\u2013106.","journal-title":"Communications of the ACM"},{"key":"2270_CR44","unstructured":"Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. In: International conference on learning representations (ICLR)."},{"key":"2270_CR45","unstructured":"Nash, C., Menick, J., Dieleman, S., & Battaglia, P. (2021). Generating images with sparse representations. In: International conference on machine learning (ICML), pp. 7958\u20137968."},{"key":"2270_CR46","doi-asserted-by":"crossref","unstructured":"Ntavelis, E., Shahbazi, M., Kastanis, I., Timofte, R., Danelljan, M., & Van Gool, L. (2022). Arbitrary-scale image synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 11533\u201311542.","DOI":"10.1109\/CVPR52688.2022.01124"},{"key":"2270_CR47","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., & Lischinski, D. (2021). StyleCLIP: Text-driven manipulation of stylegan imagery. In: Proceedings of the IEEE\/CVF international conference on computer vision (CVPR), pp. 2085\u20132094.","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"2270_CR48","doi-asserted-by":"crossref","unstructured":"Peebles, W., & Xie, S. (2023). Scalable diffusion models with transformers. In: IEEE\/CVF international conference on computer vision (ICCV), pp. 4195\u20134205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"2270_CR49","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In: International conference on machine learning (ICML), pp. 8748\u20138763."},{"key":"2270_CR50","unstructured":"Radford, A., Metz, L. and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv 2015. arXiv preprint arXiv:1511.06434."},{"issue":"6","key":"2270_CR51","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1109\/34.9115","volume":"10","author":"AP Reeves","year":"1988","unstructured":"Reeves, A. P., Prokop, R. J., Andrews, S. E., & Kuhl, F. P. (1988). Three-dimensional shape analysis using moments and Fourier descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 10(6), 937\u2013943.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2270_CR52","doi-asserted-by":"crossref","unstructured":"Richardson, E., Alaluf, Y., Patashnik, O., Nitzan, Y., Azar, Y., Shapiro, S., & Cohen-Or, D. (2021). Encoding in style: a StyleGAN encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 2287\u20132296.","DOI":"10.1109\/CVPR46437.2021.00232"},{"issue":"1","key":"2270_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544777","volume":"42","author":"D Roich","year":"2022","unstructured":"Roich, D., Mokady, R., Bermano, A. H., & Cohen-Or, D. (2022). Pivotal tuning for latent-based editing of real images. ACM Transactions on Graphics (TOG), 42(1), 1\u201313.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2270_CR54","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2270_CR55","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., & Berg, A. C. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115, 211\u2013252.","journal-title":"International journal of computer vision"},{"key":"2270_CR56","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/TPAMI.1980.4766990","volume":"2","author":"FA Sadjadi","year":"1980","unstructured":"Sadjadi, F. A., & Hall, E. L. (1980). Three-dimensional moment invariants. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2, 127\u2013136.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2270_CR57","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 29."},{"key":"2270_CR58","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., & Geiger, A. (2022). StyleGAN-XL: Scaling StyleGAN to large diverse datasets. In: ACM SIGGRAPH, pp. 1\u201310.","DOI":"10.1145\/3528233.3530738"},{"key":"2270_CR59","first-page":"17480","volume":"34","author":"A Sauer","year":"2021","unstructured":"Sauer, A., Chitta, K., M\u00fcller, J., & Geiger, A. (2021). Projected GANs converge faster. Advances in Neural Information Processing Systems (NeurIPS), 34, 17480\u201317492.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR60","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"2270_CR61","doi-asserted-by":"crossref","unstructured":"Singh, R., Shukla, A., & Turaga, P. K. (2023). Improving shape awareness and interpretability in deep networks using geometric moments. In: Deep Learning in Geometric Computing Workshop (DLGC), pp. 4159\u20134168.","DOI":"10.1109\/CVPRW59228.2023.00438"},{"key":"2270_CR62","first-page":"7462","volume":"33","author":"V Sitzmann","year":"2020","unstructured":"Sitzmann, V., Martel, J., Bergman, A., Lindell, D., & Wetzstein, G. (2020). Implicit neural representations with periodic activation functions. Advances in Neural Information Processing Systems (NeurIPS), 33, 7462\u20137473.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR63","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Ignatyev, S., & Elhoseiny, M. (2021). Adversarial generation of continuous images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10753\u201310764.","DOI":"10.1109\/CVPR46437.2021.01061"},{"key":"2270_CR64","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Menapace, W., Siarohin, A., & Tulyakov, S. (2024). Hierarchical patch diffusion models for high-resolution video generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 7569\u20137579.","DOI":"10.1109\/CVPR52733.2024.00723"},{"key":"2270_CR65","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Sotnikov, G., & Elhoseiny, M. (2021). Aligning latent and image spaces to connect the unconnectable. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp. 14144\u201314153.","DOI":"10.1109\/ICCV48922.2021.01388"},{"key":"2270_CR66","first-page":"24487","volume":"35","author":"I Skorokhodov","year":"2022","unstructured":"Skorokhodov, I., Tulyakov, S., Wang, Y., & Wonka, P. (2022). Epigraf: Rethinking training of 3d GANs. Advances in Neural Information Processing Systems (NeurIPS), 35, 24487\u201324501.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR67","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021). Score-based generative modeling through stochastic differential equations. In: International conference on learning representations (ICLR)."},{"key":"2270_CR68","unstructured":"Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning (ICML), pp. 6105\u20136114."},{"issue":"8","key":"2270_CR69","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1364\/JOSA.70.000920","volume":"70","author":"MR Teague","year":"1980","unstructured":"Teague, M. R. (1980). Image analysis via the general theory of moments. Journal of the Optical Society of America (JOSA), 70(8), 920\u2013930.","journal-title":"Journal of the Optical Society of America (JOSA)"},{"key":"2270_CR70","doi-asserted-by":"publisher","first-page":"121128","DOI":"10.1109\/ACCESS.2021.3108630","volume":"9","author":"T Theodoridis","year":"2021","unstructured":"Theodoridis, T., Loumponias, K., Vretos, N., & Daras, P. (2021). Zernike pooling: Generalizing average pooling using Zernike moments. IEEE Access, 9, 121128\u2013121136.","journal-title":"IEEE Access"},{"key":"2270_CR71","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2020). Contrastive multiview coding. In: European conference on computer vision (ECCV), pp. 776\u2013794. Springer","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"2270_CR72","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., & J\u00e9gou, H. (2021). Training data-efficient image transformers & distillation through attention. In: ICML Proceedings of machine learning research, pp. 10347\u201310357."},{"issue":"7","key":"2270_CR73","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/0167-8655(94)90069-8","volume":"15","author":"M Tuceryan","year":"1994","unstructured":"Tuceryan, M. (1994). Moment-based texture segmentation. Pattern Recognition Letters, 15(7), 659\u2013668.","journal-title":"Pattern Recognition Letters"},{"key":"2270_CR74","unstructured":"Wang, W., Bao, J., Zhou, W., Chen, D., Chen, D., Yuan, L., & Li, H. (2022). Sindiffusion: Learning a diffusion model from a single natural image. arXiv preprint arXiv:2211.12445."},{"key":"2270_CR75","unstructured":"Wang, Z., Jiang, Y., Zheng, H., Wang, P., He, P., Wang, Z., Chen, W., & Zhou, M., et\u00a0al. (2024). Patch diffusion: Faster and more data-efficient training of diffusion models. Advances in Neural Information Processing Systems (NeurIPS) 36."},{"issue":"2","key":"2270_CR76","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/83.660996","volume":"7","author":"L Wang","year":"1998","unstructured":"Wang, L., & Healey, G. (1998). Using Zernike moments for the illumination and geometry invariant classification of multispectral texture. IEEE Transactions on Image Processing, 7(2), 196\u2013203.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2270_CR77","doi-asserted-by":"crossref","unstructured":"Wu, J., Qiu, S., Kong, Y., Chen, Y., Senhadji, L., & Shu, H. (2017). MomentsNet: a simple learning-free method for binary image recognition. In: IEEE International conference on image processing (ICIP), pp. 2667\u20132671.","DOI":"10.1109\/ICIP.2017.8296766"},{"key":"2270_CR78","unstructured":"Wu, Y., Zhu, Z., Liu, F., Chrysos, G., & Cevher, V. (2022). Extrapolation and spectral bias of neural nets with hadamard product: a polynomial net study. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35."},{"issue":"12","key":"2270_CR79","doi-asserted-by":"publisher","first-page":"1996","DOI":"10.1109\/TPAMI.2005.232","volume":"27","author":"P-T Yap","year":"2005","unstructured":"Yap, P.-T., & Paramesran, R. (2005). An efficient method for the computation of Legendre moments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(12), 1996\u20132002.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2270_CR80","doi-asserted-by":"crossref","unstructured":"Yoon, Y., Chung, I., Wang, L., & Yoon, K.-J. (2022). Spheresr: 360deg image super-resolution with arbitrary projection via continuous spherical image representation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5677\u20135686.","DOI":"10.1109\/CVPR52688.2022.00559"},{"key":"2270_CR81","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., & Kanazawa, A. (2021). pixelnerf: Neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 4578\u20134587.","DOI":"10.1109\/CVPR46437.2021.00455"},{"issue":"8","key":"2270_CR82","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TIP.2011.2118216","volume":"20","author":"H Zhang","year":"2011","unstructured":"Zhang, H., Shu, H., Coatrieux, G., Zhu, J., Wu, Q. J., Zhang, Y., Zhu, H., & Luo, L. (2011). Affine Legendre moment invariants for image watermarking robust to geometric distortions. IEEE Transactions on Image Processing, 20(8), 2189\u20132199.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"2270_CR83","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1109\/TIP.2009.2036702","volume":"19","author":"H Zhang","year":"2009","unstructured":"Zhang, H., Shu, H., Han, G. N., Coatrieux, G., Luo, L., & Coatrieux, J. L. (2009). Blurred image recognition by Legendre moment invariants. IEEE Transactions on Image Processing, 19(3), 596\u2013611.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2270_CR84","first-page":"18367","volume":"34","author":"L Zhao","year":"2021","unstructured":"Zhao, L., Zhang, Z., Chen, T., Metaxas, D., & Zhang, H. (2021). Improved transformer for high-resolution (GANS). Advances in Neural Information Processing Systems (NeurIPS), 34, 18367\u201318380.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2270_CR85","unstructured":"Zheng, H., Nie, W., Vahdat, A., Azizzadenesheli, K., & Anandkumar, A. (2023). Fast sampling of diffusion models via operator learning. In: International conference on machine learning (ICLR), pp. 42390\u201342402. PMLR."},{"key":"2270_CR86","unstructured":"Zheng, H., Wang, Z., Yuan, J., Ning, G., He, P., You, Q., Yang, H., & Zhou, M. (2023). Learning stackable and skippable lego bricks for efficient, reconfigurable, and variable-resolution diffusion modeling. In: The twelfth international conference on learning representations (ICLR)."},{"key":"2270_CR87","unstructured":"Zhuang, P., Abnar, S., Gu, J., Schwing, A., Susskind, J. M., & Bautista, M. A. (2022). Diffusion probabilistic fields. In: International conference on learning representations (ICLR)."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02270-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02270-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02270-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:04:19Z","timestamp":1744869859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02270-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":87,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2270"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02270-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2024,12,20]]},"assertion":[{"value":"31 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}