GS-Net: Generalizable Plug-and-Play 3D Gaussian Splatting Module
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909318389956608 |
|---|---|
| author | Zhang, Yichen Wang, Zihan Han, Jiali Li, Peilin Zhang, Jiaxun Wang, Jianqiang He, Lei Li, Keqiang |
| author_facet | Zhang, Yichen Wang, Zihan Han, Jiali Li, Peilin Zhang, Jiaxun Wang, Jianqiang He, Lei Li, Keqiang |
| contents | 3D Gaussian Splatting (3DGS) integrates the strengths of primitive-based representations and volumetric rendering techniques, enabling real-time, high-quality rendering. However, 3DGS models typically overfit to single-scene training and are highly sensitive to the initialization of Gaussian ellipsoids, heuristically derived from Structure from Motion (SfM) point clouds, which limits both generalization and practicality. To address these limitations, we propose GS-Net, a generalizable, plug-and-play 3DGS module that densifies Gaussian ellipsoids from sparse SfM point clouds, enhancing geometric structure representation. To the best of our knowledge, GS-Net is the first plug-and-play 3DGS module with cross-scene generalization capabilities. Additionally, we introduce the CARLA-NVS dataset, which incorporates additional camera viewpoints to thoroughly evaluate reconstruction and rendering quality. Extensive experiments demonstrate that applying GS-Net to 3DGS yields a PSNR improvement of 2.08 dB for conventional viewpoints and 1.86 dB for novel viewpoints, confirming the method's effectiveness and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11307 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GS-Net: Generalizable Plug-and-Play 3D Gaussian Splatting Module Zhang, Yichen Wang, Zihan Han, Jiali Li, Peilin Zhang, Jiaxun Wang, Jianqiang He, Lei Li, Keqiang Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) integrates the strengths of primitive-based representations and volumetric rendering techniques, enabling real-time, high-quality rendering. However, 3DGS models typically overfit to single-scene training and are highly sensitive to the initialization of Gaussian ellipsoids, heuristically derived from Structure from Motion (SfM) point clouds, which limits both generalization and practicality. To address these limitations, we propose GS-Net, a generalizable, plug-and-play 3DGS module that densifies Gaussian ellipsoids from sparse SfM point clouds, enhancing geometric structure representation. To the best of our knowledge, GS-Net is the first plug-and-play 3DGS module with cross-scene generalization capabilities. Additionally, we introduce the CARLA-NVS dataset, which incorporates additional camera viewpoints to thoroughly evaluate reconstruction and rendering quality. Extensive experiments demonstrate that applying GS-Net to 3DGS yields a PSNR improvement of 2.08 dB for conventional viewpoints and 1.86 dB for novel viewpoints, confirming the method's effectiveness and robustness. |
| title | GS-Net: Generalizable Plug-and-Play 3D Gaussian Splatting Module |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.11307 |