Fast 3D Foundation Model Initialized Gaussian Splatting

[2607.03209] Fast 3D Foundation Model Initialized Gaussian Splatting Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2607.03209 (cs) [Submitted on 3 Jul 2026] Title: Fast 3D Foundation Model Initialized Gaussian Splatting Authors: Anurag Dalal , Daniel Hagen , Kjell G. Robbersmyr , Kristian Muri Knausgård View a PDF of the paper titled Fast 3D Foundation Model Initialized Gaussian Splatting, by Anurag Dalal and 2 other authors View PDF HTML (experimental) Abstract: This paper introduces a fast method for high-quality 3D Gaussian Splatting (3DGS) reconstruction without traditional Structure-from-Motion (SfM). The proposed approach leverages 3D Foundation Models (3DFMs) for camera pose and point-cloud initialization, then jointly optimizes both camera poses and Gaussian primitives using a depth-guided loss function. This enables fast convergence even from rough initialization with as few as 50-60 input views. To further improve reconstruction quality in sparse-view scenarios, an MLP-based pose refinement module is introduced alongside depth-guided supervision from the foundation model. Extensive experiments on Mip-NeRF 360, Tanks and Temples, and RobustNeRF demonstrate that the proposed method achieves competitive reconstruction quality (23.61 dB PSNR, 0.19 LPIPS) while reducing training time to approximately three minutes per scene. The proposed method produces ready-to-use 3DGS models at a fraction of the time required by existing pipelines, making it suitable for near real-time applications in robotics, VR, and autonomous navigation. Comments: 8 pages, 5 figures, 5 tables. Accepted at ICECET 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Robotics (cs.RO) ACM classes: I.2.10; I.3.6; I.3.7; I.3.8; I.4.5; I.4.8; I.4.10 Cite as: arXiv:2607.03209 [cs.CV] (or arXiv:2607.03209v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2607.03209 Focus to learn more arXiv-issued DOI via DataCite Journal reference: 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET), Rome, Italy, July 6-9, 2026 Related DOI : https://doi.org/10.1109/ICECET65726.2026.11633076 Focus to learn more DOI(s) linking to related resources Submission history From: Kristian Muri Knausgård [ view email ] [v1] Fri, 3 Jul 2026 11:24:27 UTC (2,453 KB) Full-text links: Access Paper: View a PDF of the paper titled Fast 3D Foundation Model Initialized Gaussian Splatting, by Anurag Dalal and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-07 Change to browse by: cs cs.GR cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Fast 3D Foundation Model Initialized Gaussian Splatting#608923
• 2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting#635777
• 2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting#633428
• DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting#821549
• RGS: Reflection-aware Gaussian Splatting via Learning Geometry Continuity for Reflective Objects#1014015