Rasterized Steered Mixture of Experts for Efficient 2D Image Regression
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_ | 1866908661381595136 |
|---|---|
| author | Li, Yi-Hsin Sjöström, Mårten Knorr, Sebastian Sikora, Thomas |
| author_facet | Li, Yi-Hsin Sjöström, Mårten Knorr, Sebastian Sikora, Thomas |
| contents | The Steered Mixture of Experts regression framework has demonstrated strong performance in image reconstruction, compression, denoising, and super-resolution. However, its high computational cost limits practical applications. This work introduces a rasterization-based optimization strategy that combines the efficiency of rasterized Gaussian kernel rendering with the edge-aware gating mechanism of the Steered Mixture of Experts. The proposed method is designed to accelerate two-dimensional image regression while maintaining the model's inherent sparsity and reconstruction quality. By replacing global iterative optimization with a rasterized formulation, the method achieves significantly faster parameter updates and more memory-efficient model representations. In addition, the proposed framework supports applications such as native super-resolution and image denoising, which are not directly achievable with standard rasterized Gaussian kernel approaches. The combination of fast rasterized optimization with the edge-aware structure of the Steered Mixture of Experts provides a new balance between computational efficiency and reconstruction fidelity for two-dimensional image processing tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05814 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rasterized Steered Mixture of Experts for Efficient 2D Image Regression Li, Yi-Hsin Sjöström, Mårten Knorr, Sebastian Sikora, Thomas Computer Vision and Pattern Recognition The Steered Mixture of Experts regression framework has demonstrated strong performance in image reconstruction, compression, denoising, and super-resolution. However, its high computational cost limits practical applications. This work introduces a rasterization-based optimization strategy that combines the efficiency of rasterized Gaussian kernel rendering with the edge-aware gating mechanism of the Steered Mixture of Experts. The proposed method is designed to accelerate two-dimensional image regression while maintaining the model's inherent sparsity and reconstruction quality. By replacing global iterative optimization with a rasterized formulation, the method achieves significantly faster parameter updates and more memory-efficient model representations. In addition, the proposed framework supports applications such as native super-resolution and image denoising, which are not directly achievable with standard rasterized Gaussian kernel approaches. The combination of fast rasterized optimization with the edge-aware structure of the Steered Mixture of Experts provides a new balance between computational efficiency and reconstruction fidelity for two-dimensional image processing tasks. |
| title | Rasterized Steered Mixture of Experts for Efficient 2D Image Regression |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.05814 |