{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:07:03Z","timestamp":1779311223647,"version":"3.51.4"},"reference-count":35,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Recent advances in 3D Gaussian Splatting (3DGS) have achieved state\u2010of\u2010the\u2010art results for novel view synthesis. However, efficiently capturing high\u2010fidelity reconstructions of specific objects within complex scenes remains a significant challenge. A key limitation of existing active reconstruction methods is their reliance on scene\u2010level uncertainty metrics, which are often biased by irrelevant background clutter and lead to inefficient view selection for object\u2010centric tasks. We present OUGS, a novel framework that addresses this challenge with a more principled, physically\u2010grounded uncertainty formulation for 3DGS. Our core innovation is to derive uncertainty directly from the\n                    <jats:bold>explicit physical parameters<\/jats:bold>\n                    of the 3D Gaussian primitives (e.g., position, scale, rotation). By propagating the covariance of these parameters through the rendering Jacobian, we establish a highly interpretable uncertainty model. This foundation allows us to then seamlessly integrate semantic segmentation masks to produce a targeted,\n                    <jats:bold>object\u2010aware<\/jats:bold>\n                    uncertainty score that effectively disentangles the object from its environment. This allows for a more effective active view selection strategy that prioritizes views critical to improving object fidelity. Experimental evaluations on public datasets demonstrate that our approach significantly improves the efficiency of the 3DGS reconstruction process and achieves higher quality for targeted objects compared to existing state\u2010of\u2010the\u2010art methods, while also serving as a robust uncertainty estimator for the global scene.\n                  <\/jats:p>","DOI":"10.1111\/cgf.70363","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:26:09Z","timestamp":1777562769000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["OUGS: Active View Selection via Object\u2010aware Uncertainty Estimation in 3DGS"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6914-8457","authenticated-orcid":false,"given":"Haiyi","family":"Li","sequence":"first","affiliation":[{"name":"University of Adelaide  Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8732-8049","authenticated-orcid":false,"given":"Qi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Adelaide  Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0359-206X","authenticated-orcid":false,"given":"Denis","family":"Kalkofen","sequence":"additional","affiliation":[{"name":"Graz University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0873-2698","authenticated-orcid":false,"given":"Hsiang\u2010Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Adelaide  Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"e_1_2_11_2_2","doi-asserted-by":"crossref","unstructured":"AiraL. S. ValsesiaD. MagliE.:Modeling uncertainty for gaussian splatting 2025. doi:10.1109\/TNNLS.2025.3553582. 2","DOI":"10.1109\/TNNLS.2025.3553582"},{"key":"e_1_2_11_3_2","doi-asserted-by":"crossref","unstructured":"BircherA. KamelM. AlexisK. OleynikovaH. SiegwartR.: Receding horizon \u201cnext-best-view\u201d planner for 3d exploration. InICRA(2016) pp.1462\u20131468. doi:10.1109\/ICRA.2016.7487281. 3","DOI":"10.1109\/ICRA.2016.7487281"},{"key":"e_1_2_11_4_2","doi-asserted-by":"crossref","unstructured":"BarronJ. T. MildenhallB. VerbinD. SrinivasanP. P. HedmanP.: Mip-nerf 360: Unbounded anti-aliased neural radiance fields. InCVPR(2022) pp.5460\u20135469. doi:10.1109\/CVPR52688.2022.00539. 5","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_2_11_5_2","doi-asserted-by":"crossref","unstructured":"CelarekA. KopanasG. DrettakisG. WimmerM. KerblB.:Does 3d gaussian splatting need accurate volumetric rendering? 2025. URL:https:\/\/arxiv.org\/abs\/2502.19318. 1","DOI":"10.1111\/cgf.70032"},{"key":"e_1_2_11_6_2","doi-asserted-by":"crossref","unstructured":"CortesC. A. T. LinC.-T. Do T.-T.N. ChenH.-T.: An eeg-based experiment on vr sickness and postural instability while walking in virtual environments. InIEEE Conference Virtual Reality and 3D User Interfaces (VR)(2023) p.8. 2","DOI":"10.1109\/VR55154.2023.00025"},{"issue":"11","key":"e_1_2_11_7_2","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1177\/0278364911410755","article-title":"Active vision in robotic systems: A survey of recent developments","volume":"30","author":"Chen S.","year":"2011","journal-title":"The International Journal of Robotics Research"},{"key":"e_1_2_11_8_2","unstructured":"GoliL. ReadingC. Sell\u00e1nS. JacobsonA. TagliasacchiA.: Bayes' Rays: Uncertainty quantification in neural radiance fields.CVPR(2024). 1 5 6"},{"key":"e_1_2_11_9_2","volume-title":"Digital Image Processing","author":"Gonzalez R. C.","year":"2008"},{"key":"e_1_2_11_10_2","unstructured":"HanC. DumeryC.:View-dependent uncertainty estimation of 3d gaussian splatting 2025. arXiv:2504.07370. 1 2"},{"key":"e_1_2_11_11_2","doi-asserted-by":"crossref","unstructured":"JiangW. LeiB. DaniilidisK.: Fisherrf: Active view selection and mapping with radiance fields using fisher information. InECCV(2024) pp.422\u2013440. 1 2 3 4 5 6 8","DOI":"10.1007\/978-3-031-72624-8_24"},{"key":"e_1_2_11_12_2","unstructured":"KingmaD. P. BaJ.:Adam: A method for stochastic optimization 2015. arXiv:1412.6980. 4"},{"key":"e_1_2_11_13_2","doi-asserted-by":"crossref","unstructured":"KerblB. KopanasG. LeimkuehlerT. DrettakisG.:3d gaussian splatting for real-time radiance field rendering. doi:10.1145\/3592433. 1 3 5","DOI":"10.1145\/3592433"},{"key":"e_1_2_11_14_2","doi-asserted-by":"crossref","unstructured":"KlassonM. MereuR. KannalaJ. SolinA.:Sources of uncertainty in 3d scene reconstruction 2024. 1","DOI":"10.1007\/978-3-031-91585-7_17"},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_2_11_16_2","doi-asserted-by":"crossref","unstructured":"KimM. SeoS. HanB.: Infonerf: Ray entropy minimization for few-shot neural volume rendering. InCVPR(2022) pp.12902\u201312911. doi:10.1109\/CVPR52688.2022.01257. 3","DOI":"10.1109\/CVPR52688.2022.01257"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2791"},{"key":"e_1_2_11_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2017.05.006"},{"key":"e_1_2_11_19_2","doi-asserted-by":"crossref","unstructured":"MildenhallB. SrinivasanP. P. TancikM. BarronJ. T. RamamoorthiR. NgR.: Nerf: Representing scenes as neural radiance fields for view synthesis. InCVPR(2020) pp.612\u2013621. 1","DOI":"10.1145\/3503250"},{"key":"e_1_2_11_20_2","doi-asserted-by":"crossref","unstructured":"MintonA. G. ZhuH. Y. ChenH.-T. WangY.-K. ZhuangZ. NotaroG. GalvanR. AllenJ. ZieglerM. D. LinC.-T.: A longitudinal study on the effects of circadian fatigue on sound source identification and localization using a heads-up display. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems(2025) pp.1\u201312. 1","DOI":"10.1145\/3706598.3713402"},{"key":"e_1_2_11_21_2","doi-asserted-by":"crossref","unstructured":"NiemeyerM. BarronJ. T. MildenhallB. SajjadiM. S. M. GeigerA. RadwanN.: Regnerf: Regularizing neural radiance fields for view synthesis from sparse inputs. In2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2022) pp.5470\u20135480. doi:10.1109\/CVPR52688.2022.00540. 1","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"e_1_2_11_22_2","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1007\/978-3-031-19827-4_14","volume-title":"Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXIII","author":"Pan X.","year":"2022"},{"key":"e_1_2_11_23_2","unstructured":"RaviN. et al.:Sam 2: Segment anything in images and videos 2024. arXiv:2408.00714. 6"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3235686"},{"key":"e_1_2_11_24_3","doi-asserted-by":"crossref","unstructured":"doi:10.1109\/lra.2023.3235686. 3","DOI":"10.1109\/LRA.2023.3235686"},{"key":"e_1_2_11_25_2","doi-asserted-by":"crossref","unstructured":"ShenJ. AgudoA. Moreno-NoguerF. RuizA.: Conditional-flow nerf: Accurate 3d modelling with reliable uncertainty quantification. InECCV(2022) pp.540\u2013557. 5","DOI":"10.1007\/978-3-031-20062-5_31"},{"key":"e_1_2_11_26_2","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nbergerJ. L. FrahmJ.-M.: Structure-from-motion revisited. InCVPR(2016) pp.4104\u20134113. doi:10.1109\/CVPR.2016.445. 6","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_2_11_27_2","doi-asserted-by":"crossref","unstructured":"ShenS. TanC. T. ChenH.-T. RaffeW. L. LeongT. W.: Educator perceptions of xrauthor: An accessible tool for authoring learning content with different immersion levels. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems(2025) pp.1\u201311. 1","DOI":"10.1145\/3706598.3713982"},{"key":"e_1_2_11_28_2","doi-asserted-by":"crossref","unstructured":"TanZ. ChenX. ZhangJ. FengL. HuD.:Uncertainty-aware normal-guided gaussian splatting for surface reconstruction from sparse image sequences 2025. URL:https:\/\/arxiv.org\/abs\/2503.11172 arXiv:2503.11172. 2","DOI":"10.2139\/ssrn.5928871"},{"key":"e_1_2_11_29_2","doi-asserted-by":"crossref","unstructured":"WilsonJ. AlmeidaM. MahajanS. LabrieM. GhaffariM. GhasemalizadehO. SunM. KuoC.-H. SenA.: Pop-gs: Next best view in 3d-gaussian splatting with p-optimality. InCVPR(2025) pp.3646\u20133655. doi:10.1109\/CVPR52734.2025.00345. 3 5 6","DOI":"10.1109\/CVPR52734.2025.00345"},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_11_31_2","doi-asserted-by":"crossref","unstructured":"WuR. ChenH.-T.: The effect of visual and auditory modality mismatching between distraction and warning on pedestrian street crossing behavior. InIEEE International Symposium on Mixed and Augmented Reality (ISMAR)(2023) p.8. 2","DOI":"10.1109\/ISMAR59233.2023.00121"},{"key":"e_1_2_11_32_2","doi-asserted-by":"crossref","unstructured":"XieY. CaiY. ZhangY. YangL. PanJ.:Gaussmi: Gaussian splatting shannon mutual information for active 3d reconstruction 2025. URL:https:\/\/arxiv.org\/abs\/2504.21067 arXiv:2504.21067. 3 5","DOI":"10.15607\/RSS.2025.XXI.030"},{"key":"e_1_2_11_33_2","doi-asserted-by":"crossref","unstructured":"XueS. DillJ. MathurP. DellaertF. TsiotraP. XuD.: Neural visibility field for uncertainty-driven active mapping. In2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2024) pp.18122\u201318132. doi:10.1109\/CVPR52733.2024.01716. 3","DOI":"10.1109\/CVPR52733.2024.01716"},{"key":"e_1_2_11_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2876504"},{"key":"e_1_2_11_35_2","doi-asserted-by":"crossref","unstructured":"ZhangR. IsolaP. EfrosA. A. ShechtmanE. WangO.: The unreasonable effectiveness of deep features as a perceptual metric. InCVPR(2018) pp.586\u2013595. doi:10.1109\/CVPR.2018.00068. 6","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70363","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70363","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:26:14Z","timestamp":1777562774000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70363"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":35,"alternative-id":["10.1111\/cgf.70363"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70363","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]},"assertion":[{"value":"2026-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70363"}}