Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration
Zilong Huang, Jun He, Junyan Ye, Lihan Jiang, Weijia Li, Yiping Chen, Ting Han
2025年份
5顶会引用
摘要
of China state-of-the-art method, improving by 24.24% in LPIPS and 24.40% in BRISQUE, while also achieving the fastest training speed. Additionally, to demonstrate the robustness of Scene4U and allow users to experience immersive scenes from various landmarks, we build WorldVista3D dataset for 3D scene reconstruction, which contains panoramic images of globally renowned sites. The implementation code and dataset will be made publicly available.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and LayoutsZilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong 等CVPR 2026 · 被引用 5 次
- CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View SynthesisQiwei Wang, Xianghui Ze, Jingyi Yu, Yujiao ShiICLR 2026 · 被引用 1 次
- MiDSummer: Multi-Guidance Diffusion for Controllable Zero-Shot Immersive Gaussian Splatting Scene GenerationAnjun Hu, Richard Tomsett, Valentin Gourmet, Massimo Camplani 等ICCV 2025
- PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban ScenesChristina Ourania Tze, Daniel Dauner, Yiyi Liao, Dzmitry Tsishkou 等CVPR 2026
- Top2Pano: Learning to Generate Indoor Panoramas from Top-Down ViewZitong Zhang, Suranjan Gautam, Rui YuICCV 2025
它引用的顶会 Paper25
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt 等NeurIPS 2021 · 被引用 2,500 次
- Zero-1-to-3: Zero-shot One Image to 3D ObjectRuoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov 等ICCV 2023 · 被引用 1,662 次
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen 等CVPR 2022 · 被引用 1,237 次
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape OptimizationMinghua Liu, Chao Xu, Haian Jin, Linghao Chen 等NeurIPS 2023 · 被引用 755 次
相关 Paper
- PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian SplattingCheng Zhang, Haofei Xu, Qianyi Wu, Camilo Cruz Gambardella 等CVPR 2025
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D ReconstructionSeungtae Nam, Xiangyu Sun, Gyeongjin Kang, Younggeun Lee 等CVPR 2025
- Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed ViewsChong Bao, Xiyu Zhang, Zehao Yu, Jiale Shi 等CVPR 2025
- LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulationChenxu Zhou, Lvchang Fu, Sida Peng, Yunzhi Yan 等CVPR 2025
- Merge3D: Efficient 3D Multimodal LLMs via Joint 2D-3D Token MergingTianbo Pan, Xingyi Yang, Xinchao WangCVPR 2026
