Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929738623221760 |
|---|---|
| author | Shen, You Zhang, Zhipeng Li, Xinyang Qu, Yansong Lin, Yu Zhang, Shengchuan Cao, Liujuan |
| author_facet | Shen, You Zhang, Zhipeng Li, Xinyang Qu, Yansong Lin, Yu Zhang, Shengchuan Cao, Liujuan |
| contents | Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed. Yet, due to the unstructured and irregular nature of Gaussian point clouds, ensuring accurate geometry reconstruction remains difficult. Existing methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks. However, the former suffers from inherent conflicts between rendering and reconstruction, while the latter is computationally and storage-intensive. To address these challenges, we propose CarGS, a unified model leveraging Contribution-adaptive regularization to achieve simultaneous, high-quality rendering and surface reconstruction. The essence of our framework is learning adaptive contribution for Gaussian primitives by squeezing the knowledge from geometry regularization into a compact MLP. Additionally, we introduce a geometry-guided densification strategy with clues from both normals and Signed Distance Fields (SDF) to improve the capability of capturing high-frequency details. Our design improves the mutual learning of the two tasks, meanwhile its unified structure does not require separate models as in dual-model based approaches, guaranteeing efficiency. Extensive experiments demonstrate the ability to achieve state-of-the-art (SOTA) results in both rendering fidelity and reconstruction accuracy while maintaining real-time speed and minimal storage size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00881 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization Shen, You Zhang, Zhipeng Li, Xinyang Qu, Yansong Lin, Yu Zhang, Shengchuan Cao, Liujuan Computer Vision and Pattern Recognition Artificial Intelligence Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed. Yet, due to the unstructured and irregular nature of Gaussian point clouds, ensuring accurate geometry reconstruction remains difficult. Existing methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks. However, the former suffers from inherent conflicts between rendering and reconstruction, while the latter is computationally and storage-intensive. To address these challenges, we propose CarGS, a unified model leveraging Contribution-adaptive regularization to achieve simultaneous, high-quality rendering and surface reconstruction. The essence of our framework is learning adaptive contribution for Gaussian primitives by squeezing the knowledge from geometry regularization into a compact MLP. Additionally, we introduce a geometry-guided densification strategy with clues from both normals and Signed Distance Fields (SDF) to improve the capability of capturing high-frequency details. Our design improves the mutual learning of the two tasks, meanwhile its unified structure does not require separate models as in dual-model based approaches, guaranteeing efficiency. Extensive experiments demonstrate the ability to achieve state-of-the-art (SOTA) results in both rendering fidelity and reconstruction accuracy while maintaining real-time speed and minimal storage size. |
| title | Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.00881 |