Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.23042 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916815120105472 |
|---|---|
| author | Nguyen, Hung Le, An Li, Runfa Nguyen, Truong |
| author_facet | Nguyen, Hung Le, An Li, Runfa Nguyen, Truong |
| contents | 3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primitives that strains memory and bandwidth. We introduce AutoOpti3DGS, a training-time framework that automatically restrains Gaussian proliferation without sacrificing visual fidelity. The key idea is to feed the input images to a sequence of learnable Forward and Inverse Discrete Wavelet Transforms, where low-pass filters are kept fixed, high-pass filters are learnable and initialized to zero, and an auxiliary orthogonality loss gradually activates fine frequencies. This wavelet-driven, coarse-to-fine process delays the formation of redundant fine Gaussians, allowing 3DGS to capture global structure first and refine detail only when necessary. Through extensive experiments, AutoOpti3DGS requires just a single filter learning-rate hyper-parameter, integrates seamlessly with existing efficient 3DGS frameworks, and consistently produces sparser scene representations more compatible with memory or storage-constrained hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23042 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting Nguyen, Hung Le, An Li, Runfa Nguyen, Truong Computer Vision and Pattern Recognition 3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primitives that strains memory and bandwidth. We introduce AutoOpti3DGS, a training-time framework that automatically restrains Gaussian proliferation without sacrificing visual fidelity. The key idea is to feed the input images to a sequence of learnable Forward and Inverse Discrete Wavelet Transforms, where low-pass filters are kept fixed, high-pass filters are learnable and initialized to zero, and an auxiliary orthogonality loss gradually activates fine frequencies. This wavelet-driven, coarse-to-fine process delays the formation of redundant fine Gaussians, allowing 3DGS to capture global structure first and refine detail only when necessary. Through extensive experiments, AutoOpti3DGS requires just a single filter learning-rate hyper-parameter, integrates seamlessly with existing efficient 3DGS frameworks, and consistently produces sparser scene representations more compatible with memory or storage-constrained hardware. |
| title | From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.23042 |