{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:05:48Z","timestamp":1780931148237,"version":"3.54.1"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.113957","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:30:19Z","timestamp":1779305419000},"page":"113957","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["OPa-Ma: Text guided Mamba for 360-degree image out-painting"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1935-5752","authenticated-orcid":false,"given":"Penglei","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4623-0365","authenticated-orcid":false,"given":"Kai","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0169-457X","authenticated-orcid":false,"given":"Tiandi","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven Z.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2384-4702","authenticated-orcid":false,"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-6931","authenticated-orcid":false,"given":"Xiaofeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113957_b1","doi-asserted-by":"crossref","unstructured":"T. Hara, Y. Mukuta, T. Harada, Spherical image generation from a single image by considering scene symmetry, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 1513\u20131521.","DOI":"10.1609\/aaai.v35i2.16242"},{"key":"10.1016\/j.patcog.2026.113957_b2","doi-asserted-by":"crossref","unstructured":"Z. Lu, K. Hu, C. Wang, L. Bai, Z. Wang, Autoregressive omni-aware outpainting for open-vocabulary 360-degree image generation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 14211\u201314219.","DOI":"10.1609\/aaai.v38i13.29332"},{"key":"10.1016\/j.patcog.2026.113957_b3","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113957_b4","series-title":"European Conference on Computer Vision","first-page":"148","article-title":"Zigma: A dit-style zigzag mamba diffusion model","author":"Hu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113957_b5","series-title":"Painting outside the box: Image outpainting with gans","author":"Sabini","year":"2018"},{"key":"10.1016\/j.patcog.2026.113957_b6","doi-asserted-by":"crossref","unstructured":"Z. Yang, J. Dong, P. Liu, Y. Yang, S. Yan, Very long natural scenery image prediction by outpainting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 10561\u201310570.","DOI":"10.1109\/ICCV.2019.01066"},{"key":"10.1016\/j.patcog.2026.113957_b7","doi-asserted-by":"crossref","unstructured":"C.-N. Lu, Y.-C. Chang, W.-C. Chiu, Bridging the visual gap: Wide-range image blending, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 843\u2013851.","DOI":"10.1109\/CVPR46437.2021.00090"},{"key":"10.1016\/j.patcog.2026.113957_b8","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention is all you need, in: Advances in Annual Conference on Neural Information Processing Systems, 2017, pp. 5998\u20136008."},{"key":"10.1016\/j.patcog.2026.113957_b9","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"2286","article-title":"Convit: Improving vision transformers with soft convolutional inductive biases","author":"D\u2019Ascoli","year":"2021"},{"key":"10.1016\/j.patcog.2026.113957_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109659","article-title":"Improved robustness of vision transformers via prelayernorm in patch embedding","volume":"141","author":"Kim","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113957_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2023.02.021","article-title":"Generalised image outpainting with u-transformer","volume":"162","author":"Gao","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.113957_b12","doi-asserted-by":"crossref","unstructured":"K. Yao, P. Gao, X. Yang, J. Sun, R. Zhang, K. Huang, Outpainting by queries, in: Proceedings of the European Conference on Computer Vision, 2022, pp. 153\u2013169.","DOI":"10.1007\/978-3-031-20050-2_10"},{"key":"10.1016\/j.patcog.2026.113957_b13","doi-asserted-by":"crossref","unstructured":"H. Chang, H. Zhang, L. Jiang, C. Liu, W.T. Freeman, Maskgit: Masked generative image transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11315\u201311325.","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"10.1016\/j.patcog.2026.113957_b14","doi-asserted-by":"crossref","unstructured":"P. Esser, R. Rombach, B. Ommer, Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12873\u201312883.","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"10.1016\/j.patcog.2026.113957_b15","article-title":"Easyoutpainter: One step image outpainting with both continuous multiple and resolution","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113957_b16","article-title":"Self-prompt guided image outpainting model for captions absence in social scenes","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.patcog.2026.113957_b17","doi-asserted-by":"crossref","unstructured":"C. LeGendre, W.-C. Ma, G. Fyffe, J. Flynn, L. Charbonnel, J. Busch, P. Debevec, Deeplight: Learning illumination for unconstrained mobile mixed reality, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5918\u20135928.","DOI":"10.1109\/CVPR.2019.00607"},{"key":"10.1016\/j.patcog.2026.113957_b18","doi-asserted-by":"crossref","unstructured":"P. Phongthawee, W. Chinchuthakun, N. Sinsunthithet, V. Jampani, A. Raj, P. Khungurn, S. Suwajanakorn, Diffusionlight: Light probes for free by painting a chrome ball, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 98\u2013108.","DOI":"10.1109\/CVPR52733.2024.00018"},{"key":"10.1016\/j.patcog.2026.113957_b19","doi-asserted-by":"crossref","unstructured":"Z. Wang, J. Philion, S. Fidler, J. Kautz, Learning indoor inverse rendering with 3d spatially-varying lighting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 12538\u201312547.","DOI":"10.1109\/ICCV48922.2021.01231"},{"key":"10.1016\/j.patcog.2026.113957_b20","series-title":"2019 IEEE International Conference on Image Processing","first-page":"4704","article-title":"360-Degree image completion by two-stage conditional gans","author":"Akimoto","year":"2019"},{"key":"10.1016\/j.patcog.2026.113957_b21","doi-asserted-by":"crossref","unstructured":"N. Akimoto, Y. Matsuo, Y. Aoki, Diverse plausible 360-degree image outpainting for efficient 3dcg background creation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11441\u201311450.","DOI":"10.1109\/CVPR52688.2022.01115"},{"key":"10.1016\/j.patcog.2026.113957_b22","doi-asserted-by":"crossref","unstructured":"G. Somanath, D. Kurz, Hdr environment map estimation for real-time augmented reality, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11298\u201311306.","DOI":"10.1109\/CVPR46437.2021.01114"},{"key":"10.1016\/j.patcog.2026.113957_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107320","article-title":"Panogen++: Domain-adapted text-guided panoramic environment generation for vision-and-language navigation","volume":"187","author":"Wang","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.113957_b24","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.patcog.2026.113957_b25","doi-asserted-by":"crossref","unstructured":"S. Gao, P. Zhou, M.-M. Cheng, S. Yan, Masked diffusion transformer is a strong image synthesizer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 23164\u201323173.","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"10.1016\/j.patcog.2026.113957_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110799","article-title":"Denoising diffusion post-processing for low-light image enhancement","volume":"156","author":"Panagiotou","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113957_b27","series-title":"International Conference on Machine Learning","first-page":"1280","article-title":"Probabilistic recurrent state-space models","author":"Doerr","year":"2018"},{"key":"10.1016\/j.patcog.2026.113957_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109375","article-title":"Time series clustering with an em algorithm for mixtures of linear gaussian state space models","volume":"138","author":"Umatani","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113957_b29","series-title":"International Conference on Machine Learning","first-page":"62429","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113957_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105569","article-title":"Efficient mamba: overcoming the visual limitations of mamba with innovative structures","volume":"161","author":"Xu","year":"2025","journal-title":"Image Vis. Comput."},{"issue":"1","key":"10.1016\/j.patcog.2026.113957_b31","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/s11263-025-02597-y","article-title":"Video mamba suite: State space model as a versatile alternative for video understanding","volume":"134","author":"Chen","year":"2026","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113957_b32","series-title":"Medical Image Computing and Computer Assisted Intervention","first-page":"578","article-title":"Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation","author":"Xing","year":"2024"},{"key":"10.1016\/j.patcog.2026.113957_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125518","article-title":"Selective and multi-scale fusion mamba for medical image segmentation","volume":"261","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113957_b34","series-title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113957_b35","doi-asserted-by":"crossref","unstructured":"N. Yang, Y. Wang, Z. Liu, M. Li, Y. An, X. Zhao, Smamba: Sparse mamba for event-based object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 2025, pp. 9229\u20139237.","DOI":"10.1609\/aaai.v39i9.32999"},{"key":"10.1016\/j.patcog.2026.113957_b36","doi-asserted-by":"crossref","unstructured":"M.A. Ahamed, Q. Cheng, Timemachine: A time series is worth 4 mambas for long-term forecasting, in: ECAI 2024: 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain-Including 13th Conference on Prestigious Applications of Intelligent Systems. European Conference on Artificial Intelli, Vol. 392, 2024, p. 1688.","DOI":"10.3233\/FAIA240677"},{"key":"10.1016\/j.patcog.2026.113957_b37","series-title":"Denoising Diffusion Probabilistic Models","first-page":"6840","volume":"Vol. 33","author":"Ho","year":"2020"},{"issue":"6","key":"10.1016\/j.patcog.2026.113957_b38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3130800.3130891","article-title":"Learning to predict indoor illumination from a single image","volume":"36","author":"Gardner","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.patcog.2026.113957_b39","doi-asserted-by":"crossref","unstructured":"J. Zhang, J.-F. Lalonde, Learning high dynamic range from outdoor panoramas, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 4519\u20134528.","DOI":"10.1109\/ICCV.2017.484"},{"key":"10.1016\/j.patcog.2026.113957_b40","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113957_b41","doi-asserted-by":"crossref","unstructured":"M. Cherti, R. Beaumont, R. Wightman, M. Wortsman, G. Ilharco, C. Gordon, C. Schuhmann, L. Schmidt, J. Jitsev, Reproducible scaling laws for contrastive language-image learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2818\u20132829.","DOI":"10.1109\/CVPR52729.2023.00276"},{"issue":"4","key":"10.1016\/j.patcog.2026.113957_b42","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1007\/s11633-025-1562-4","article-title":"Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models","volume":"22","author":"Lu","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.patcog.2026.113957_b43","doi-asserted-by":"crossref","unstructured":"R. Zhang, P. Isola, A.A. Efros, E. Shechtman, O. Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.patcog.2026.113957_b44","series-title":"Advances in Neural Information Processing Systems","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017"},{"key":"10.1016\/j.patcog.2026.113957_b45","doi-asserted-by":"crossref","unstructured":"G. Parmar, R. Zhang, J.-Y. Zhu, On aliased resizing and surprising subtleties in gan evaluation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11410\u201311420.","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"10.1016\/j.patcog.2026.113957_b46","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","first-page":"3982","article-title":"Sentence-bert: Sentence embeddings using siamese bert-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.patcog.2026.113957_b47","series-title":"Advances in Neural Information Processing Systems","first-page":"2226","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016"},{"issue":"6","key":"10.1016\/j.patcog.2026.113957_b48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550454.3555447","article-title":"Text2light: Zero-shot text-driven hdr panorama generation","volume":"41","author":"Chen","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.patcog.2026.113957_b49","series-title":"2022 International Conference on 3D Vision","first-page":"475","article-title":"Guided co-modulated gan for 360 field of view extrapolation","author":"Dastjerdi","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009222?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009222?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:49:18Z","timestamp":1780930158000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":49,"alternative-id":["S0031320326009222"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113957","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OPa-Ma: Text guided Mamba for 360-degree image out-painting","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113957","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113957"}}