{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T14:16:18Z","timestamp":1774361778539,"version":"3.50.1"},"reference-count":40,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100004410","name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Single\u2010image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry\u2010aware self\u2010correction framework that leverages the model's own normal and depth predictions to refine structural accuracy. Unlike prior approaches that rely solely on features extracted from the input image, GeoFusionLRM feeds back geometric cues through a dedicated transformer and fusion module, enabling the model to correct errors and enforce consistency with the conditioning image. This design improves the alignment between the reconstructed mesh and the input views without additional supervision or external signals. Extensive experiments demonstrate that GeoFusionLRM achieves sharper geometry, more consistent normals, and higher fidelity than state\u2010of\u2010the\u2010art LRM baselines.<\/jats:p>","DOI":"10.1111\/cgf.70325","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:26:20Z","timestamp":1774358780000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GeoFusionLRM: Geometry\u2010Aware Self\u2010Correction for Consistent 3D Reconstruction"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3312-4280","authenticated-orcid":false,"given":"Ahmet Burak","family":"Yildirim","sequence":"first","affiliation":[{"name":"Bilkent University  Ankara Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8780-3028","authenticated-orcid":false,"given":"Tuna","family":"Saygin","sequence":"additional","affiliation":[{"name":"Bilkent University  Ankara Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2307-9052","authenticated-orcid":false,"given":"Duygu","family":"Ceylan","sequence":"additional","affiliation":[{"name":"Adobe Research  London United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2014-6325","authenticated-orcid":false,"given":"Aysegul","family":"Dundar","sequence":"additional","affiliation":[{"name":"Bilkent University  Ankara Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"e_1_2_7_2_2","doi-asserted-by":"crossref","unstructured":"BhattadA. DundarA. LiuG. TaoA. CatanzaroB.: View generalization for single image textured 3d models. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2021) pp.6081\u20136090. 2","DOI":"10.1109\/CVPR46437.2021.00602"},{"key":"e_1_2_7_3_2","unstructured":"ChenW. LingH. GaoJ. SmithE. LehtinenJ. JacobsonA. FidlerS.: Learning to predict 3d objects with an interpolation-based differentiable renderer. InAdvances in Neural Information Processing Systems(2019) pp.9609\u20139619. 2"},{"key":"e_1_2_7_4_2","doi-asserted-by":"crossref","unstructured":"CaronM. TouvronH. MisraI. J\u00e9gouH. MairalJ. BojanowskiP. JoulinA.: Emerging properties in self-supervised vision transformers. InProceedings of the International Conference on Computer Vision (ICCV)(2021). 2 3","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_2_7_5_2","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1109\/ICRA46639.2022.9811809","volume-title":"2022 International Conference on Robotics and Automation (ICRA)","author":"Downs L.","year":"2022"},{"issue":"12","key":"e_1_2_7_6_2","doi-asserted-by":"crossref","first-page":"14563","DOI":"10.1109\/TPAMI.2023.3319429","article-title":"Fine detailed texture learning for 3d meshes with generative models","volume":"45","author":"Dundar A.","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"e_1_2_7_7_2","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1109\/TPAMI.2023.3324806","article-title":"Progressive learning of 3d reconstruction network from 2d gan data","volume":"46","author":"Dundar A.","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_7_8_2","doi-asserted-by":"crossref","unstructured":"DeitkeM. SchwenkD. SalvadorJ. WeihsL. MichelO. VanderBiltE. SchmidtL. EhsaniK. KembhaviA. FarhadiA.: Objaverse: A universe of annotated 3d objects. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2023) pp.13142\u201313153. 4","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_2_7_9_2","first-page":"241","volume-title":"European Conference on Computer Vision","author":"Fu X.","year":"2024"},{"key":"e_1_2_7_10_2","unstructured":"GoelS. KanazawaA. MalikJ.: Shape and viewpoint without keypoints.arXiv preprint arXiv:2007.10982(2020). 2"},{"key":"e_1_2_7_11_2","doi-asserted-by":"crossref","unstructured":"HuangZ. BossM. VasishtaA. RehgJ. M. JampaniV.: Spar3d: Stable point-aware reconstruction of 3d objects from single images. InProceedings of the Computer Vision and Pattern Recognition Conference(2025) pp.16860\u201316870. 1 5","DOI":"10.1109\/CVPR52734.2025.01571"},{"key":"e_1_2_7_12_2","unstructured":"HeZ. WangT.:Openlrm: Open-source large reconstruction models.https:\/\/github.com\/3DTopia\/OpenLRM 2023. Accessed: 2025-09-26. 5"},{"key":"e_1_2_7_13_2","unstructured":"HongY. ZhangK. GuJ. BiS. ZhouY. LiuD. LiuF. SunkavalliK. BuiT. TanH.: LRM: Large reconstruction model for single image to 3D.arXiv preprint arXiv:2311.04400(2023). URL:https:\/\/arxiv.org\/abs\/2311.04400 arXiv: 2311.04400. 1 2 5"},{"key":"e_1_2_7_14_2","unstructured":"JiangH. HuangQ. PavlakosG.:Real3d: Scaling up large reconstruction models with real-world images. 1"},{"key":"e_1_2_7_15_2","unstructured":"KangG. NamS. SunX. KhamisS. MohamedA. ParkE.: ilrm: An iterative large 3d reconstruction model.arXiv preprint arXiv:2507.23277(2025). 3"},{"key":"e_1_2_7_16_2","unstructured":"LabsB. F.:Flux.https:\/\/github.com\/black-forest-labs\/flux 2024. 1"},{"key":"e_1_2_7_17_2","doi-asserted-by":"crossref","unstructured":"LongX. GuoY.-C. LinC. LiuY. DouZ. LiuL. MaY. ZhangS.-H. HabermannM. TheobaltC. et al.: Wonder3d: Single image to 3d using cross-domain diffusion. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(2024) pp.9970\u20139980. 3","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"e_1_2_7_18_2","first-page":"55975","article-title":"Era3d: High-resolution multiview diffusion using efficient row-wise attention","volume":"37","author":"Li P.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_7_19_2","unstructured":"LiJ. TanH. ZhangK. XuZ. LuanF. XuY. HongY. SunkavalliK. ShakhnarovichG. BiS.: Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model.arXiv preprint arXiv:2311.06214(2023). 1 2"},{"key":"e_1_2_7_20_2","doi-asserted-by":"crossref","unstructured":"LiZ. WangD. ChenK. LvZ. Nguyen-PhuocT. LeeM. HuangJ.-B. XiaoL. ZhuY. MarshallC. S. et al.: Lirm: Large inverse rendering model for progressive reconstruction of shape materials and view-dependent radiance fields. InProceedings of the Computer Vision and Pattern Recognition Conference(2025) pp.505\u2013517. 3","DOI":"10.1109\/CVPR52734.2025.00056"},{"key":"e_1_2_7_21_2","doi-asserted-by":"crossref","unstructured":"LiuR. WuR. Van HoorickB. TokmakovP. ZakharovS. VondrickC.: Zero-1-to-3: Zero-shot one image to 3d object. InProceedings of the IEEE\/CVF international conference on computer vision(2023) pp.9298\u20139309. 1 3","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"e_1_2_7_22_2","first-page":"22226","article-title":"One-2-3-45: Any single image to 3d mesh in 45 seconds without pershape optimization","volume":"36","author":"Liu M.","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_2_7_23_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3728293","article-title":"Normal-guided detail-preserving neural implicit function for high-fidelity 3d surface reconstruction","volume":"8","author":"Patel A.","year":"2025","journal-title":"Proceedings of the ACM on computer graphics and interactive techniques"},{"key":"e_1_2_7_24_2","unstructured":"ShiR. ChenH. ZhangZ. LiuM. XuC. WeiX. ChenL. ZengC. SuH.: Zero123++: a single image to consistent multi-view diffusion base model.arXiv preprint arXiv:2310.15110(2023). 2 3"},{"key":"e_1_2_7_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592430"},{"key":"e_1_2_7_25_3","doi-asserted-by":"crossref","unstructured":"doi:10.1145\/3592430. 4","DOI":"10.1145\/3592430"},{"key":"e_1_2_7_26_2","unstructured":"ShiY. WangP. YeJ. LongM. LiK. YangX.: Mvdream: Multi-view diffusion for 3d generation.arXiv preprint arXiv:2308.16512(2023). 1"},{"key":"e_1_2_7_27_2","doi-asserted-by":"crossref","unstructured":"ShenY. ZhouK. WangH. YangY. ShaoT.: High-fidelity 3d object generation from single image with rgbn-volume gaussian reconstruction model. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(June2025) pp.21558\u201321569. 3","DOI":"10.1109\/CVPR52734.2025.02008"},{"key":"e_1_2_7_28_2","first-page":"1","volume-title":"European Conference on Computer Vision","author":"Tang J.","year":"2024"},{"key":"e_1_2_7_29_2","unstructured":"TochilkinD. PankratzD. LiuZ. HuangZ. LettsA. LiY. LiangD. LaforteC. JampaniV. CaoY.-P.: Triposr: Fast 3d object reconstruction from a single image.arXiv preprint arXiv:2403.02151(2024). 2"},{"key":"e_1_2_7_30_2","doi-asserted-by":"crossref","unstructured":"TangJ. WangT. ZhangB. ZhangT. YiR. MaL. ChenD.: Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior. InProceedings of the IEEE\/CVF international conference on computer vision(2023) pp.22819\u201322829. 3","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"e_1_2_7_31_2","first-page":"439","volume-title":"European Conference on Computer Vision","author":"Voleti V.","year":"2024"},{"key":"e_1_2_7_32_2","unstructured":"WangP. ShiY.: Imagedream: Image-prompt multi-view diffusion for 3d generation.arXiv preprint arXiv:2312.02201(2023). 1"},{"key":"e_1_2_7_33_2","unstructured":"WangP. TanH. BiS. XuY. LuanF. SunkavalliK. WangW. XuZ. ZhangK.: Pf-lrm: Pose-free large reconstruction model for joint pose and shape prediction.arXiv preprint arXiv:2311.12024(2023). 1 3"},{"key":"e_1_2_7_34_2","unstructured":"WeiX. ZhangK. BiS. TanH. LuanF. DeschaintreV. SunkavalliK. SuH. XuZ.: Meshlrm: Large reconstruction model for high-quality mesh.arXiv preprint arXiv:2404.12385(2024). 1"},{"key":"e_1_2_7_35_2","doi-asserted-by":"crossref","unstructured":"WuT. ZhangJ. FuX. WangY. RenJ. PanL. WuW. YangL. WangJ. QianC. et al.: Omniobject3d: Large-vocabulary 3d object dataset for realistic perception reconstruction and generation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2023) pp.803\u2013814. 4","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"e_1_2_7_36_2","first-page":"53285","article-title":"Lrm-zero: Training large reconstruction models with synthesized data","volume":"37","author":"Xie D.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_7_37_2","unstructured":"XuJ. ChengW. GaoY. WangX. GaoS. ShanY.: Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models.arXiv preprint arXiv:2404.07191(2024). 1 2 3 5"},{"key":"e_1_2_7_38_2","unstructured":"ZhuangP. HanS. WangC. SiarohinA. ZouJ. VasilkovskyM. ShakhraiV. KorolevS. TulyakovS. LeeH.-Y.: Gtr: Improving large 3d reconstruction models through geometry and texture refinement.arXiv preprint arXiv:2406.05649(2024). 3"},{"key":"e_1_2_7_39_2","doi-asserted-by":"crossref","unstructured":"ZhangR. IsolaP. EfrosA. A. ShechtmanE. WangO.: The unreasonable effectiveness of deep features as a perceptual metric. InCVPR(2018). 4","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_7_40_2","doi-asserted-by":"crossref","unstructured":"ZhengX.-Y. PanH. GuoY.-X. TongX. LiuY.: Mvd\u02c6 2: Efficient multiview 3d reconstruction for multiview diffusion. InACM SIGGRAPH 2024 conference papers(2024) pp.1\u201311. 3","DOI":"10.1145\/3641519.3657403"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70325","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70325","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:26:43Z","timestamp":1774358803000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":40,"alternative-id":["10.1111\/cgf.70325"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70325","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]},"assertion":[{"value":"2026-03-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70325"}}