CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912332844630016 |
|---|---|
| author | Tong, Yifei Tian, Runze Han, Xiao Liu, Dingyao Yu, Fenggen Zhang, Yan |
| author_facet | Tong, Yifei Tian, Runze Han, Xiao Liu, Dingyao Yu, Fenggen Zhang, Yan |
| contents | As 3D Gaussian Splatting (3DGS) gains popularity as a 3D representation of real scenes, enabling user-friendly deformation to create novel scenes while preserving fine details from the original 3DGS has attracted significant research attention. We introduce CAGE-GS, a cage-based 3DGS deformation method that seamlessly aligns a source 3DGS scene with a user-defined target shape. Our approach learns a deformation cage from the target, which guides the geometric transformation of the source scene. While the cages effectively control structural alignment, preserving the textural appearance of 3DGS remains challenging due to the complexity of covariance parameters. To address this, we employ a Jacobian matrix-based strategy to update the covariance parameters of each Gaussian, ensuring texture fidelity post-deformation. Our method is highly flexible, accommodating various target shape representations, including texts, images, point clouds, meshes and 3DGS models. Extensive experiments and ablation studies on both public datasets and newly proposed scenes demonstrate that our method significantly outperforms existing techniques in both efficiency and deformation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12800 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation Tong, Yifei Tian, Runze Han, Xiao Liu, Dingyao Yu, Fenggen Zhang, Yan Graphics Computer Vision and Pattern Recognition As 3D Gaussian Splatting (3DGS) gains popularity as a 3D representation of real scenes, enabling user-friendly deformation to create novel scenes while preserving fine details from the original 3DGS has attracted significant research attention. We introduce CAGE-GS, a cage-based 3DGS deformation method that seamlessly aligns a source 3DGS scene with a user-defined target shape. Our approach learns a deformation cage from the target, which guides the geometric transformation of the source scene. While the cages effectively control structural alignment, preserving the textural appearance of 3DGS remains challenging due to the complexity of covariance parameters. To address this, we employ a Jacobian matrix-based strategy to update the covariance parameters of each Gaussian, ensuring texture fidelity post-deformation. Our method is highly flexible, accommodating various target shape representations, including texts, images, point clouds, meshes and 3DGS models. Extensive experiments and ablation studies on both public datasets and newly proposed scenes demonstrate that our method significantly outperforms existing techniques in both efficiency and deformation quality. |
| title | CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.12800 |