Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians
Changfeng Ma, Ran Bi, Jie Guo, Chongjun Wang, Yanwen Guo
2025Year
Abstract
Generalize to Other Categories Car Figure 1. Our method excels in rendering intricate, photo-realistic images from point clouds of different categories. In this instance, our model is trained on the Car category, utilizing 20K points as input.
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.
Builds on12
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP FrameworkXu Ma, Can Qin, Haoxuan You, Haoxi Ran et al.ICLR 2022 · 841 citations
- 2D Gaussian Splatting for Geometrically Accurate Radiance FieldsBinbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger et al.SIGGRAPH 2024 · 660 citations
- POCO: Point Convolution for Surface ReconstructionAlexandre Boulch, Renaud MarletCVPR 2022 · 128 citations
- ADOP: approximate differentiable one-pixel point renderingDarius Rückert, Linus Franke, Marc StammingerSIGGRAPH 2022 · 127 citations
Related papers
- SynSin: End-to-End View Synthesis From a Single ImageOlivia Wiles, Georgia Gkioxari, Richard Szeliski, Justin JohnsonCVPR 2020
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D ReconstructionSeungtae Nam, Xiangyu Sun, Gyeongjin Kang, Younggeun Lee et al.CVPR 2025
- Patch-Based 3D Natural Scene Generation from a Single ExampleWeiyu Li, Xuelin Chen, Jue Wang, Baoquan ChenCVPR 2023
- Ponder: Point Cloud Pre-training via Neural RenderingDi Huang, Sida Peng, Tong He, Honghui Yang et al.ICCV 2023 · 55 citations
- Real3D: Towards Scaling Large Reconstruction Models with Real ImagesHanwen Jiang, Qixing Huang, Georgios PavlakosICCV 2025 · 3 citations
