C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images
Methods based on 3D Gaussian Splatting (3DGS) for surface reconstruction face challenges when applied to large-scale scenes captured by UAV. Because the number of 3D Gaussians increases dramatically, leading to significant computational requirement and limiting the fineness of surface reconstruction...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10839501/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542622356340736 |
|---|---|
| author | Jiating Qian Yiming Yan Fengjiao Gao Baoyu Ge Maosheng Wei Boyi Shangguan Guangjun He |
| author_facet | Jiating Qian Yiming Yan Fengjiao Gao Baoyu Ge Maosheng Wei Boyi Shangguan Guangjun He |
| author_sort | Jiating Qian |
| collection | DOAJ |
| description | Methods based on 3D Gaussian Splatting (3DGS) for surface reconstruction face challenges when applied to large-scale scenes captured by UAV. Because the number of 3D Gaussians increases dramatically, leading to significant computational requirement and limiting the fineness of surface reconstruction. To address this challenge, we propose C3DGS that compresses 3D Gaussian model and ensures the quality of surface reconstruction of large-scale scenes in the face of heavy computational costs. Our method quantifies the contribution of 3D Gaussians to the surface reconstruction and prunes redundant 3D Gaussians to reduce the computational requirement of the model. In addition, pruning 3D Gaussians inevitably incurs loss, and in order to guarantee as many details as possible in the surface reconstruction of a complex scene, we use a ray tracing volume rendering method that can better evaluate the opacity of 3D Gaussians. Furthermore, we introduce two regularization terms to enhance the geometric consistency of multiple views, thus improving the realism of surface reconstruction. Experiments show that our method outperforms other 3DGS-based surface reconstruction methods when facing large-scale scenes. |
| format | Article |
| id | doaj-art-eed2b7c24d714f10bda6526cbd1306e1 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-eed2b7c24d714f10bda6526cbd1306e12025-02-04T00:00:27ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184396440910.1109/JSTARS.2025.352926110839501C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV ImagesJiating Qian0https://orcid.org/0009-0002-6583-7322Yiming Yan1https://orcid.org/0000-0003-0751-7726Fengjiao Gao2Baoyu Ge3Maosheng Wei4Boyi Shangguan5Guangjun He6https://orcid.org/0000-0002-2614-8850Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology and College of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaKey Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology and College of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaIntelligent Manufacturing Research Institute, Heilongjiang Academy of Sciences, Harbin, ChinaHarbin Space Star Data System Technology Company Ltd., Harbin, ChinaHarbin Space Star Data System Technology Company Ltd., Harbin, ChinaState Key Laboratory of Space-earth Integrated Information Technology, Beijing Institute of Satellite Information Engineering, Beijing, ChinaState Key Laboratory of Space-earth Integrated Information Technology, Beijing Institute of Satellite Information Engineering, Beijing, ChinaMethods based on 3D Gaussian Splatting (3DGS) for surface reconstruction face challenges when applied to large-scale scenes captured by UAV. Because the number of 3D Gaussians increases dramatically, leading to significant computational requirement and limiting the fineness of surface reconstruction. To address this challenge, we propose C3DGS that compresses 3D Gaussian model and ensures the quality of surface reconstruction of large-scale scenes in the face of heavy computational costs. Our method quantifies the contribution of 3D Gaussians to the surface reconstruction and prunes redundant 3D Gaussians to reduce the computational requirement of the model. In addition, pruning 3D Gaussians inevitably incurs loss, and in order to guarantee as many details as possible in the surface reconstruction of a complex scene, we use a ray tracing volume rendering method that can better evaluate the opacity of 3D Gaussians. Furthermore, we introduce two regularization terms to enhance the geometric consistency of multiple views, thus improving the realism of surface reconstruction. Experiments show that our method outperforms other 3DGS-based surface reconstruction methods when facing large-scale scenes.https://ieeexplore.ieee.org/document/10839501/3D Gaussian splatting (3DGS)large-scale scenesmultiview UAV imagessurface reconstruction |
| spellingShingle | Jiating Qian Yiming Yan Fengjiao Gao Baoyu Ge Maosheng Wei Boyi Shangguan Guangjun He C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 3D Gaussian splatting (3DGS) large-scale scenes multiview UAV images surface reconstruction |
| title | C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images |
| title_full | C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images |
| title_fullStr | C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images |
| title_full_unstemmed | C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images |
| title_short | C3DGS: Compressing 3D Gaussian Model for Surface Reconstruction of Large-Scale Scenes Based on Multiview UAV Images |
| title_sort | c3dgs compressing 3d gaussian model for surface reconstruction of large scale scenes based on multiview uav images |
| topic | 3D Gaussian splatting (3DGS) large-scale scenes multiview UAV images surface reconstruction |
| url | https://ieeexplore.ieee.org/document/10839501/ |
| work_keys_str_mv | AT jiatingqian c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages AT yimingyan c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages AT fengjiaogao c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages AT baoyuge c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages AT maoshengwei c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages AT boyishangguan c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages AT guangjunhe c3dgscompressing3dgaussianmodelforsurfacereconstructionoflargescalescenesbasedonmultiviewuavimages |