Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes
Lihan Jiang, Kerui Ren, Mulin Yu, Linning Xu, Junting Dong, Tao Lu, Feng Zhao, Dahua Lin, Bo Dai
Abstract
Figure 1 . Horizon-GS enables high-quality rendering and reconstruction of aerial-to-ground scenes with unprecedented fidelity across scales, supporting drastic view changes. The colored camera trajectories in the center illustrate the novel viewpoints, while the reconstructed mesh is overlaid on the scene. The surrounding images show the corresponding predicted images for each viewpoint. Explore more demos on our project page: https://city-super.github.io/horizon-gs/ .
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext e88c1da5-a168-41d2-98cd-ad2ff4d15f01Cited by top-tier papers9
- Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian SplattingYuanyuan Gao, YUNING GONG, Yifei Liu, Jingfeng Li et al.CVPR 2026 · 6 citations
- EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View SynthesisYancheng Zhang, Guangyu Sun, Chen ChenNeurIPS 2025 · 2 citations
- GS-Occ3D: Scaling Vision-Only Occupancy Reconstruction with Gaussian SplattingBaijun Ye, Minghui Qin, Saining Zhang, Moonjun Goon et al.ICCV 2025 · 2 citations
- ObjectGS: Object-Aware Scene Reconstruction and Scene Understanding via Gaussian SplattingRuijie Zhu, Mulin Yu, Linning Xu, Lihan Jiang et al.ICCV 2025 · 1 citation
- A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene ReconstructionFelix Windisch, Thomas Köhler, Lukas Radl, Mattia D'Urso et al.SIGGRAPH 2026
Builds on23
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
- Neural Sparse Voxel FieldsLingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua et al.NeurIPS 2020 · 1,535 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
Related papers
- AerialMegaDepth: Learning Aerial-Ground Reconstruction and View SynthesisKhiem Vuong, Anurag Ghosh, Deva Ramanan, Srinivasa G. Narasimhan et al.CVPR 2025
- Monocular Neural Image Based Rendering With Continuous View ControlJie Song, Xu Chen, Otmar HilligesICCV 2019 · 85 citations
- Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced ImagesMatias Turkulainen, Akshay Krishnan, Filippo Aleotti, Mohamed Sayed et al.CVPR 2026
- AccidentalGS: 3D Gaussian Splatting from Accidental Camera MotionMao Mao, Xujie Shen, Guyuan Chen, Boming Zhao et al.ICCV 2025 · 1 citation
- Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene ReconstructionDongxu Wei, Zhiqi Li, Peidong LiuCVPR 2025
