Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2411.05731 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916737722613760 |
|---|---|
| author | Jin, Junxi Li, Xiulai Huang, Haiping Liu, Lianjun Sun, Yujie Liu, Logan |
| author_facet | Jin, Junxi Li, Xiulai Huang, Haiping Liu, Lianjun Sun, Yujie Liu, Logan |
| contents | Recently, 3D Gaussian Splatting (3D-GS) has achieved significant success in real-time, high-quality 3D scene rendering. However, it faces several challenges, including Gaussian redundancy, limited ability to capture view-dependent effects, and difficulties in handling complex lighting and specular reflections. Additionally, methods that use spherical harmonics for color representation often struggle to effectively capture anisotropic components, especially when modeling view-dependent colors under complex lighting conditions, leading to insufficient contrast and unnatural color saturation. To address these limitations, we introduce PEP-GS, a perceptually-enhanced framework that dynamically predicts Gaussian attributes, including opacity, color, and covariance. We replace traditional spherical harmonics with a Hierarchical Granular-Structural Attention mechanism, which enables more accurate modeling of complex view-dependent color effects. By employing a stable and interpretable framework for opacity and covariance estimation, PEP-GS avoids the removal of essential Gaussians prematurely, ensuring a more accurate scene representation. Furthermore, perceptual optimization is applied to the final rendered images, enhancing perceptual consistency across different views and ensuring high-quality renderings with improved texture fidelity and fine-scale detail preservation. Experimental results demonstrate that PEP-GS outperforms state-of-the-art methods, particularly in challenging scenarios involving view-dependent effects and fine-scale details. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05731 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PEP-GS: Perceptually-Enhanced Precise Structured 3D Gaussians for View-Adaptive Rendering Jin, Junxi Li, Xiulai Huang, Haiping Liu, Lianjun Sun, Yujie Liu, Logan Computer Vision and Pattern Recognition Recently, 3D Gaussian Splatting (3D-GS) has achieved significant success in real-time, high-quality 3D scene rendering. However, it faces several challenges, including Gaussian redundancy, limited ability to capture view-dependent effects, and difficulties in handling complex lighting and specular reflections. Additionally, methods that use spherical harmonics for color representation often struggle to effectively capture anisotropic components, especially when modeling view-dependent colors under complex lighting conditions, leading to insufficient contrast and unnatural color saturation. To address these limitations, we introduce PEP-GS, a perceptually-enhanced framework that dynamically predicts Gaussian attributes, including opacity, color, and covariance. We replace traditional spherical harmonics with a Hierarchical Granular-Structural Attention mechanism, which enables more accurate modeling of complex view-dependent color effects. By employing a stable and interpretable framework for opacity and covariance estimation, PEP-GS avoids the removal of essential Gaussians prematurely, ensuring a more accurate scene representation. Furthermore, perceptual optimization is applied to the final rendered images, enhancing perceptual consistency across different views and ensuring high-quality renderings with improved texture fidelity and fine-scale detail preservation. Experimental results demonstrate that PEP-GS outperforms state-of-the-art methods, particularly in challenging scenarios involving view-dependent effects and fine-scale details. |
| title | PEP-GS: Perceptually-Enhanced Precise Structured 3D Gaussians for View-Adaptive Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.05731 |