Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting
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_ | 1866909764839014400 |
|---|---|
| author | Lee, Jee Won Lim, Hansol Yang, Sooyeun Choi, Jongseong Brad |
| author_facet | Lee, Jee Won Lim, Hansol Yang, Sooyeun Choi, Jongseong Brad |
| contents | High-fidelity 3D Gaussian Splatting methods excel at capturing fine textures but often overlook model compactness, resulting in massive splat counts, bloated memory, long training, and complex post-processing. We present Micro-Splatting: Two-Stage Adaptive Growth and Refinement, a unified, in-training pipeline that preserves visual detail while drastically reducing model complexity without any post-processing or auxiliary neural modules. In Stage I (Growth), we introduce a trace-based covariance regularization to maintain near-isotropic Gaussians, mitigating low-pass filtering in high-frequency regions and improving spherical-harmonic color fitting. We then apply gradient-guided adaptive densification that subdivides splats only in visually complex regions, leaving smooth areas sparse. In Stage II (Refinement), we prune low-impact splats using a simple opacity-scale importance score and merge redundant neighbors via lightweight spatial and feature thresholds, producing a lean yet detail-rich model. On four object-centric benchmarks, Micro-Splatting reduces splat count and model size by up to 60% and shortens training by 20%, while matching or surpassing state-of-the-art PSNR, SSIM, and LPIPS in real-time rendering. These results demonstrate that Micro-Splatting delivers both compactness and high fidelity in a single, efficient, end-to-end framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05740 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting Lee, Jee Won Lim, Hansol Yang, Sooyeun Choi, Jongseong Brad Graphics Computer Vision and Pattern Recognition High-fidelity 3D Gaussian Splatting methods excel at capturing fine textures but often overlook model compactness, resulting in massive splat counts, bloated memory, long training, and complex post-processing. We present Micro-Splatting: Two-Stage Adaptive Growth and Refinement, a unified, in-training pipeline that preserves visual detail while drastically reducing model complexity without any post-processing or auxiliary neural modules. In Stage I (Growth), we introduce a trace-based covariance regularization to maintain near-isotropic Gaussians, mitigating low-pass filtering in high-frequency regions and improving spherical-harmonic color fitting. We then apply gradient-guided adaptive densification that subdivides splats only in visually complex regions, leaving smooth areas sparse. In Stage II (Refinement), we prune low-impact splats using a simple opacity-scale importance score and merge redundant neighbors via lightweight spatial and feature thresholds, producing a lean yet detail-rich model. On four object-centric benchmarks, Micro-Splatting reduces splat count and model size by up to 60% and shortens training by 20%, while matching or surpassing state-of-the-art PSNR, SSIM, and LPIPS in real-time rendering. These results demonstrate that Micro-Splatting delivers both compactness and high fidelity in a single, efficient, end-to-end framework. |
| title | Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05740 |