MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910604414943232 |
|---|---|
| author | Xie, Shuzhao Zhang, Weixiang Tang, Chen Bai, Yunpeng Lu, Rongwei Ge, Shijia Wang, Zhi |
| author_facet | Xie, Shuzhao Zhang, Weixiang Tang, Chen Bai, Yunpeng Lu, Rongwei Ge, Shijia Wang, Zhi |
| contents | 3D Gaussian Splatting demonstrates excellent quality and speed in novel view synthesis. Nevertheless, the huge file size of the 3D Gaussians presents challenges for transmission and storage. Current works design compact models to replace the substantial volume and attributes of 3D Gaussians, along with intensive training to distill information. These endeavors demand considerable training time, presenting formidable hurdles for practical deployment. To this end, we propose MesonGS, a codec for post-training compression of 3D Gaussians. Initially, we introduce a measurement criterion that considers both view-dependent and view-independent factors to assess the impact of each Gaussian point on the rendering output, enabling the removal of insignificant points. Subsequently, we decrease the entropy of attributes through two transformations that complement subsequent entropy coding techniques to enhance the file compression rate. More specifically, we first replace rotation quaternions with Euler angles; then, we apply region adaptive hierarchical transform to key attributes to reduce entropy. Lastly, we adopt finer-grained quantization to avoid excessive information loss. Moreover, a well-crafted finetune scheme is devised to restore quality. Extensive experiments demonstrate that MesonGS significantly reduces the size of 3D Gaussians while preserving competitive quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09756 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation Xie, Shuzhao Zhang, Weixiang Tang, Chen Bai, Yunpeng Lu, Rongwei Ge, Shijia Wang, Zhi Computer Vision and Pattern Recognition 3D Gaussian Splatting demonstrates excellent quality and speed in novel view synthesis. Nevertheless, the huge file size of the 3D Gaussians presents challenges for transmission and storage. Current works design compact models to replace the substantial volume and attributes of 3D Gaussians, along with intensive training to distill information. These endeavors demand considerable training time, presenting formidable hurdles for practical deployment. To this end, we propose MesonGS, a codec for post-training compression of 3D Gaussians. Initially, we introduce a measurement criterion that considers both view-dependent and view-independent factors to assess the impact of each Gaussian point on the rendering output, enabling the removal of insignificant points. Subsequently, we decrease the entropy of attributes through two transformations that complement subsequent entropy coding techniques to enhance the file compression rate. More specifically, we first replace rotation quaternions with Euler angles; then, we apply region adaptive hierarchical transform to key attributes to reduce entropy. Lastly, we adopt finer-grained quantization to avoid excessive information loss. Moreover, a well-crafted finetune scheme is devised to restore quality. Extensive experiments demonstrate that MesonGS significantly reduces the size of 3D Gaussians while preserving competitive quality. |
| title | MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.09756 |