Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910899101499392 |
|---|---|
| author | Ma, Jingui Hu, Yang Tang, Luyang Yang, Jiayu Zhai, Yongqi Wang, Ronggang |
| author_facet | Ma, Jingui Hu, Yang Tang, Luyang Yang, Jiayu Zhai, Yongqi Wang, Ronggang |
| contents | Recently, 3D Gaussian Spatting (3DGS) has gained widespread attention in Novel View Synthesis (NVS) due to the remarkable real-time rendering performance. However, the substantial cost of storage and transmission of vanilla 3DGS hinders its further application (hundreds of megabytes or even gigabytes for a single scene). Motivated by the achievements of prediction in video compression, we introduce the prediction technique into the anchor-based Gaussian representation to effectively reduce the bit rate. Specifically, we propose a spatial condition-based prediction module to utilize the grid-captured scene information for prediction, with a residual compensation strategy designed to learn the missing fine-grained information. Besides, to further compress the residual, we propose an instance-aware hyper prior, developing a structure-aware and instance-aware entropy model. Extensive experiments demonstrate the effectiveness of our prediction-based compression framework and each technical component. Even compared with SOTA compression method, our framework still achieves a bit rate savings of 24.42 percent. Code is to be released! |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23337 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction Ma, Jingui Hu, Yang Tang, Luyang Yang, Jiayu Zhai, Yongqi Wang, Ronggang Computer Vision and Pattern Recognition Multimedia Recently, 3D Gaussian Spatting (3DGS) has gained widespread attention in Novel View Synthesis (NVS) due to the remarkable real-time rendering performance. However, the substantial cost of storage and transmission of vanilla 3DGS hinders its further application (hundreds of megabytes or even gigabytes for a single scene). Motivated by the achievements of prediction in video compression, we introduce the prediction technique into the anchor-based Gaussian representation to effectively reduce the bit rate. Specifically, we propose a spatial condition-based prediction module to utilize the grid-captured scene information for prediction, with a residual compensation strategy designed to learn the missing fine-grained information. Besides, to further compress the residual, we propose an instance-aware hyper prior, developing a structure-aware and instance-aware entropy model. Extensive experiments demonstrate the effectiveness of our prediction-based compression framework and each technical component. Even compared with SOTA compression method, our framework still achieves a bit rate savings of 24.42 percent. Code is to be released! |
| title | Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2503.23337 |