VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917555763937280 |
|---|---|
| author | Li, Aoduo Li, Jiancheng Ye, Huan Xu, Hongjian Wu, Shiting Zhang, Xiujun Li, Zimeng Chen, Xuhang |
| author_facet | Li, Aoduo Li, Jiancheng Ye, Huan Xu, Hongjian Wu, Shiting Zhang, Xiujun Li, Zimeng Chen, Xuhang |
| contents | 3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption due to millions of Gaussian primitives. Existing pruning methods rely on heuristic importance scores or synchronous batch updates, leading to suboptimal compression and training instability. We propose VEDAL, a principled framework that formulates Gaussian pruning as variational free energy minimization. Our approach introduces (1) a prediction-error gating mechanism that asynchronously activates pruning based on per-Gaussian reconstruction uncertainty, and (2) a variational uncertainty head that models pruning decisions as latent variables with learnable priors. The free energy objective naturally balances reconstruction fidelity against model complexity through an information-theoretic lens. Extensive experiments on Mip-NeRF 360, Tanks&Temples, and Deep Blending demonstrate that VEDAL achieves 5.2x compression with only 0.31 dB PSNR drop, outperforming PUP 3D-GS by +0.05 dB at a higher compression ratio and LightGaussian by +0.35 dB at comparable quality, while maintaining real-time rendering at 185 FPS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02346 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning Li, Aoduo Li, Jiancheng Ye, Huan Xu, Hongjian Wu, Shiting Zhang, Xiujun Li, Zimeng Chen, Xuhang Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) achieves remarkable novel view synthesis quality with real-time rendering, yet suffers from excessive memory consumption due to millions of Gaussian primitives. Existing pruning methods rely on heuristic importance scores or synchronous batch updates, leading to suboptimal compression and training instability. We propose VEDAL, a principled framework that formulates Gaussian pruning as variational free energy minimization. Our approach introduces (1) a prediction-error gating mechanism that asynchronously activates pruning based on per-Gaussian reconstruction uncertainty, and (2) a variational uncertainty head that models pruning decisions as latent variables with learnable priors. The free energy objective naturally balances reconstruction fidelity against model complexity through an information-theoretic lens. Extensive experiments on Mip-NeRF 360, Tanks&Temples, and Deep Blending demonstrate that VEDAL achieves 5.2x compression with only 0.31 dB PSNR drop, outperforming PUP 3D-GS by +0.05 dB at a higher compression ratio and LightGaussian by +0.35 dB at comparable quality, while maintaining real-time rendering at 185 FPS. |
| title | VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.02346 |