Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
Dongxu Wei, Zhiqi Li, Peidong Liu
2025Year
14Top-tier citations
Abstract
Input Views (real or synthetic) Novel Views Inference Rendering Reconstructed Scenes Figure 1. Provided with six surrounding images captured in real world or synthesized by 2D diffusion models, we can generate high-quality 3D Gaussians based on our Omni-Gaussian representation for ego-centric scene reconstruction and novel view synthesis.
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 b24a7159-17ce-4aa3-aaa3-5a9b9f22fc7dCited by top-tier papers14
- WorldGen: From Text to Traversable and Interactive 3D WorldsDilin Wang, Hyunyoung Jung, Tom Monnier, Kihyuk Sohn et al.CVPR 2026 · 24 citations
- DVGT: Driving Visual Geometry TransformerSicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu et al.CVPR 2026 · 23 citations
- SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature AlignmentQi Xu, Dongxu Wei, Lingzhe Zhao, Wenpu Li et al.NeurIPS 2025 · 19 citations
- WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous DrivingZiyue Zhu, Zhanqian Wu, Zhenxin Zhu, Lijun Zhou et al.ICLR 2026 · 11 citations
- UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene ReconstructionChen Shi, Shaoshuai Shi, Xiaoyang Lyu, Chunyang Liu et al.ICLR 2026 · 10 citations
Builds on29
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou et al.ICCV 2021 · 8,921 citations
- 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
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
Related papers
- Omnidirectional 3D Scene Reconstruction from Single ImageRen Yang, Jiahao Li, Yan LuNeurIPS 2025
- CAT3D: Create Anything in 3D with Multi-View Diffusion ModelsRuiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee et al.NeurIPS 2024 · 490 citations
- MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar ReconstructionZijian Dong, Longteng Duan, Jie Song, Michael J. Black et al.ICCV 2025 · 4 citations
- UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-View ImagesJiamin Wu, Kenkun Liu, Xiaoke Jiang, Yuan Yao et al.ICCV 2025 · 3 citations
- SfM-Free 3D Gaussian Splatting via Hierarchical TrainingBo Ji, Angela YaoCVPR 2025
