Dual-Dimensional Gaussian Splatting Integrating 2D and 3D Gaussians for Surface Reconstruction
Source abstract
Abstract
Three-Dimensional Gaussian Splatting (3DGS) has revolutionized novel-view synthesis, enabling real-time rendering of high-quality scenes. Two-Dimensional Gaussian Splatting (2DGS) improves geometric accuracy by replacing 3D Gaussians with flat 2D Gaussians. However, the flat nature of 2D Gaussians reduces mesh quality on volumetric surfaces and results in over-smoothed reconstruction. To address this, we propose Dual-Dimensional Gaussian Splatting (DDGS), which integrates both 2D and 3D Gaussians. First, we generalize the homogeneous transformation matrix based on 2DGS to initialize all Gaussians in 3D. Subsequently, during training, we selectively convert Gaussians into 2D representations based on their scale. This approach leverages the complementary strengths of 2D and 3D Gaussians, resulting in more accurate surface reconstruction across both flat and volumetric regions. Additionally, to mitigate over-smoothing, we introduce gradient-based regularization terms. Quantitative evaluations on the DTU and TnT datasets demonstrate that DDGS consistently outperforms prior methods, including 3DGS, SuGaR, and 2DGS, achieving the best Chamfer Distance and F1 score across a wide range of scenes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Optical measurement and interference techniques · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronics Engineering, Chungbuk National University, 1 Chungdae-ro, Seowon-gu, Cheongju 28644, Republic of Korea
Funding
National Research Foundation of Korea (NRF) · Korea Institute for Advancement of Technology (KIAT) · Institute of Information & Communications Technology Planning & Evaluation
References (37)
Show source-provided references
1. Tang, J., Ren, J., Zhou, H., Liu, Z., and Zeng, G. (2023). Dreamgaussian: Generative gaussian splatting for efficient 3D content creation. arXiv.
2. Tang, J., Chen, Z., Chen, X., Wang, T., Zeng, G., and Liu, Z. (29–4, January 29). Lgm: Large multi-view gaussian model for high-resolution 3D content creation. Proceedings of the European Conference on Computer Vision, Milan, Italy.
3. Tonderski, A., Lindström, C., Hess, G., Ljungbergh, W., Svensson, L., and Petersson, C. (2024, January 16–22). Neurad: Neural rendering for autonomous driving. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.01411 ↗
4. Wang, J., Zhu, X., Chen, Z., Li, P., Jiang, C., Zhang, H., Yu, C., and Yu, B. (2025). SRNeRF: Super-Resolution Neural Radiance Fields for Autonomous Driving Scenario Reconstruction from Sparse Views. World Electr. Veh. J., 16.10.3390/wevj16020066 ↗
5. Fov-nerf: Foveated neural radiance fields for virtual reality10.1109/TVCG.2022.3203102 ↗
6. Lian, H., Liu, K., Cao, R., Fei, Z., Wen, X., and Chen, L. (2024). Integration of 3D Gaussian Splatting and Neural Radiance Fields in Virtual Reality Fire Fighting. Remote Sens., 16.10.3390/rs16132448 ↗
7. Abramov, N., Lankegowda, H., Liu, S., Barazzetti, L., Beltracchi, C., and Ruttico, P. (2024). Implementing Immersive Worlds for Metaverse-Based Participatory Design through Photogrammetry and Blockchain. ISPRS Int. J. Geo-Inf., 13.10.3390/ijgi13060211 ↗
8. Fabra, L., Solanes, J.E., Muñoz, A., Martí-Testón, A., Alabau, A., and Gracia, L. (2024). Application of Neural Radiance Fields (NeRFs) for 3D model representation in the industrial metaverse. Appl. Sci., 14.10.3390/app14051825 ↗
9. 3D gaussian splatting for real-time radiance field rendering10.1145/3592433 ↗
10. Huang, B., Yu, Z., Chen, A., Geiger, A., and Gao, S. (August, January 27). 2d gaussian splatting for geometrically accurate radiance fields. Proceedings of the ACM SIGGRAPH 2024 Conference Papers, Denver, CO, USA.10.1145/3641519.3657428 ↗
11. Zhou, Q.Y., Park, J., and Koltun, V. (2018). Open3D: A modern library for 3D data processing. arXiv.
12. Lu, T., Yu, M., Xu, L., Xiangli, Y., Wang, L., Lin, D., and Dai, B. (2024, January 16–22). Scaffold-gs: Structured 3D gaussians for view-adaptive rendering. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.01952 ↗
13. Lightgaussian: Unbounded 3D gaussian compression with 15x reduction and 200+ fps
14. Qiu, S., Wu, C., Wan, Z., and Tong, S. (2025). High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity. Appl. Sci., 15.10.3390/app15031535 ↗
15. Guo, C., Gao, C., Bai, Y., and Lv, X. (2024). RD-SLAM: Real-Time Dense SLAM Using Gaussian Splatting. Appl. Sci., 14.10.3390/app14177767 ↗
16. Zhu, F., Zhao, Y., Chen, Z., Jiang, C., Zhu, H., and Hu, X. (2025). DyGS-SLAM: Realistic Map Reconstruction in Dynamic Scenes Based on Double-Constrained Visual SLAM. Remote Sens., 17.10.3390/rs17040625 ↗
17. Ma, X., Song, C., Ji, Y., and Zhong, S. (2025). Related Keyframe Optimization Gaussian–Simultaneous Localization and Mapping: A 3D Gaussian Splatting-Based Simultaneous Localization and Mapping with Related Keyframe Optimization. Appl. Sci., 15.10.3390/app15031320 ↗
18. Choi, S., Song, H., Kim, J., Kim, T., and Do, H. (October, January 29). Click-gaussian: Interactive segmentation to any 3D gaussians. Proceedings of the European Conference on Computer Vision, Milan, Italy.
19. Dong, S., Ding, L., Huang, Z., Wang, Z., Xue, T., and Xu, D. (2024, January 16–22). Interactive3d: Create what you want by interactive 3D generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.00478 ↗
20. Liu, Y., Luo, C., Fan, L., Wang, N., Peng, J., and Zhang, Z. (October, January 29). Citygaussian: Real-time high-quality large-scale scene rendering with gaussians. Proceedings of the European Conference on Computer Vision, Milan, Italy.
21. Shaheen, B., Zane, M.D., Bui, B.T., Huang, T., Merello, M., Scheelk, B., Crooks, S., and Wu, M. (2025). ForestSplat: Proof-of-Concept for a Scalable and High-Fidelity Forestry Mapping Tool Using 3D Gaussian Splatting. Remote Sens., 17.10.3390/rs17060993 ↗
22. Mu, Y., Zuo, X., Guo, C., Wang, Y., Lu, J., Wu, X., Xu, S., Dai, P., Yan, Y., and Cheng, L. (October, January 29). Gsd: View-guided gaussian splatting diffusion for 3D reconstruction. Proceedings of the European Conference on Computer Vision, Milan, Italy.
23. Mithun, N.C., Pham, T., Wang, Q., Southall, B., Minhas, K., Matei, B., Mandt, S., Samarasekera, S., and Kumar, R. (2025). Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis. arXiv.
24. Lou, H., Liu, Y., Pan, Y., Geng, Y., Chen, J., Ma, W., Li, C., Wang, L., Feng, H., and Shi, L. (2024). Robo-gs: A physics consistent spatial-temporal model for robotic arm with hybrid representation. arXiv.
25. Guédon, A., and Lepetit, V. (2024, January 16–22). Sugar: Surface-aligned gaussian splatting for efficient 3D mesh reconstruction and high-quality mesh rendering. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.00512 ↗
26. Splatloc: 3D gaussian splatting-based visual localization for augmented reality10.1109/TVCG.2025.3549563 ↗
27. Chen, H., Li, C., and Lee, G.H. (2023). Neusg: Neural implicit surface reconstruction with 3D gaussian splatting guidance. arXiv.
28. Turkulainen, M., Ren, X., Melekhov, I., Seiskari, O., Rahtu, E., and Kannala, J. (2024). Dn-splatter: Depth and normal priors for gaussian splatting and meshing. arXiv.10.1109/WACV61041.2025.00241 ↗
29. Lin, J., Gu, J., Fan, L., Wu, B., Lou, Y., Chen, R., Liu, L., and Ye, J. (2024). HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting. arXiv.
30. Chen, P., Wei, X., Wuwu, Q., Wang, X., Xiao, X., and Lu, M. (2024). MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting. arXiv.
31. Zhou, Q., Gong, Y., Yang, W., Li, J., Luo, Y., Xu, B., Li, S., Fei, B., and He, Y. (2025). MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions. arXiv.
32. Zwicker, M., Rasanen, J., Botsch, M., Dachsbacher, C., and Pauly, M. (2004, January 17–19). Perspective accurate splatting. Proceedings of the Graphics Interface, London, ON, Canada.
33. Hahlbohm, F., Friederichs, F., Weyrich, T., Franke, L., Kappel, M., Castillo, S., Stamminger, M., Eisemann, M., and Magnor, M. (2024). Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency. arXiv.10.1111/cgf.70014 ↗
34. Blinn, J.F. (1977, January 20–22). A homogeneous formulation for lines in 3 space. Proceedings of the 4th Annual Conference on Computer Graphics and Interactive Techniques, San Jose, CA, USA.10.1145/563858.563900 ↗
35. Jensen, R., Dahl, A., Vogiatzis, G., Tola, E., and Aanæs, H. (2014, January 23–28). Large scale multi-view stereopsis evaluation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.59 ↗
36. Tanks and temples: Benchmarking large-scale scene reconstruction10.1145/3072959.3073599 ↗
37. Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., and Hedman, P. (2022, January 18–24). Mip-nerf 360: Unbounded anti-aliased neural radiance fields. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00539 ↗