Fast Feedforward 3D Gaussian Splatting Compression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912270514126848 |
|---|---|
| author | Chen, Yihang Wu, Qianyi Li, Mengyao Lin, Weiyao Harandi, Mehrtash Cai, Jianfei |
| author_facet | Chen, Yihang Wu, Qianyi Li, Mengyao Lin, Weiyao Harandi, Mehrtash Cai, Jianfei |
| contents | With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed, previous art suffers from a common limitation: for any existing 3DGS, per-scene optimization is needed to achieve compression, making the compression sluggish and slow. To address this issue, we introduce Fast Compression of 3D Gaussian Splatting (FCGS), an optimization-free model that can compress 3DGS representations rapidly in a single feed-forward pass, which significantly reduces compression time from minutes to seconds. To enhance compression efficiency, we propose a multi-path entropy module that assigns Gaussian attributes to different entropy constraint paths for balance between size and fidelity. We also carefully design both inter- and intra-Gaussian context models to remove redundancies among the unstructured Gaussian blobs. Overall, FCGS achieves a compression ratio of over 20X while maintaining fidelity, surpassing most per-scene SOTA optimization-based methods. Our code is available at: https://github.com/YihangChen-ee/FCGS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08017 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fast Feedforward 3D Gaussian Splatting Compression Chen, Yihang Wu, Qianyi Li, Mengyao Lin, Weiyao Harandi, Mehrtash Cai, Jianfei Computer Vision and Pattern Recognition With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed, previous art suffers from a common limitation: for any existing 3DGS, per-scene optimization is needed to achieve compression, making the compression sluggish and slow. To address this issue, we introduce Fast Compression of 3D Gaussian Splatting (FCGS), an optimization-free model that can compress 3DGS representations rapidly in a single feed-forward pass, which significantly reduces compression time from minutes to seconds. To enhance compression efficiency, we propose a multi-path entropy module that assigns Gaussian attributes to different entropy constraint paths for balance between size and fidelity. We also carefully design both inter- and intra-Gaussian context models to remove redundancies among the unstructured Gaussian blobs. Overall, FCGS achieves a compression ratio of over 20X while maintaining fidelity, surpassing most per-scene SOTA optimization-based methods. Our code is available at: https://github.com/YihangChen-ee/FCGS. |
| title | Fast Feedforward 3D Gaussian Splatting Compression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.08017 |