Patch-Based 3D Natural Scene Generation from a Single Example
Weiyu Li, Xuelin Chen, Jue Wang, Baoquan Chen
2023Year
7Top-tier citations
Abstract
Figure 1. From a single example (inset), our method can generate diverse samples with highly realistic geometric structure and visual appearance. None of existing 3D generative models can achieve these results. More generated samples that are intricate and intriguing, ranging from single-object scenes (e.g., plants) to mid-scale ones, and large terrains, can be found in Section 4 and the supplementary.
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 371c786a-00d6-475a-ba28-1ff6663ac371Cited by top-tier papers7
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured ShapeRundi Wu, Ruoshi Liu, Carl Vondrick, Changxi ZhengICLR 2024 · 34 citations
- ThemeStation: Generating Theme-Aware 3D Assets from Few ExemplarsZhenwei Wang, Tengfei Wang, Gerhard P. Hancke, Ziwei Liu et al.SIGGRAPH 2024 · 7 citations
- NuiScene: Exploring Efficient Generation of Unbounded Outdoor ScenesHan-Hung Lee, Qinghong Han, Angel X. ChangICCV 2025 · 5 citations
- Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view DiffusionZeren Xiong, Zikun Chen, Zedong Zhang, Xiang Li et al.ACM MM 2025 · 2 citations
- PEGAsus: 3D Personalization of Geometry and AppearanceJingyu Hu, Bin Hu, Ka-Hei Hui, Haipeng Li et al.SIGGRAPH 2026
Builds on25
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Volume Rendering of Neural Implicit SurfacesLior Yariv, Jiatao Gu, Yoni Kasten, Yaron LipmanNeurIPS 2021 · 1,421 citations
- PlenOctrees for Real-time Rendering of Neural Radiance FieldsAlex Yu, Ruilong Li, Matthew Tancik, Hao Li et al.ICCV 2021 · 1,284 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
Related papers
- Infinite Photorealistic Worlds Using Procedural GenerationAlexander Raistrick, Lahav Lipson, Zeyu Ma, Lingjie Mei et al.CVPR 2023
- Real3D: Towards Scaling Large Reconstruction Models with Real ImagesHanwen Jiang, Qixing Huang, Georgios PavlakosICCV 2025 · 3 citations
- Multi-View 3D Reconstruction of a Texture-Less Smooth Surface of Unknown Generic ReflectanceZiang Cheng, Hongdong Li, Yuta Asano, Yinqiang Zheng et al.CVPR 2021
- MIDI: Multi-Instance Diffusion for Single Image to 3D Scene GenerationZehuan Huang, Yuan-Chen Guo, Xingqiao An, Yunhan Yang et al.CVPR 2025
- Sparse Point Cloud Patches Rendering via Splitting 2D GaussiansChangfeng Ma, Ran Bi, Jie Guo, Chongjun Wang et al.CVPR 2025
