探索对于摆脱3D高斯点渲染中的模糊陷阱至关重要
Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting
- Hunan University（湖南大学）
- Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究3D高斯点渲染中模糊陷阱问题，通过数学分析确定其两种类型，提出随机播种和随机分割策略减轻模糊陷阱，经实验验证可有效克服该问题，实现高质量渲染。
AI中文摘要：
3D高斯点渲染（3DGS）采用高斯基元进行显式场景表示，便于对复杂场景进行实时、高保真重建和新视图合成。然而，3DGS中固有的显式建模在优化过程中引入了梯度偏差，使其非凸优化过程极易收敛到局部次优解，即模糊陷阱。为解决此限制，我们将简单的显式探索集成到3DGS优化框架中。首先，通过对3DGS优化公式的严格数学分析，确定导致模糊陷阱的潜在优化偏差并将其分为两种不同类型：远侧模糊陷阱和近侧模糊陷阱。随后，我们提出两种非常简单的探索策略（随机播种和随机分割）分别减轻远侧和近侧模糊陷阱。实验验证表明，纳入这些探索算子可有效且互补地克服模糊陷阱，在多个数据集上实现高质量渲染性能。
英文摘要：
3D Gaussian Splatting (3DGS) employs Gaussian primitives for explicit scene representation, facilitating real-time, high-fidelity reconstruction and novel view synthesis of complex scenes. However, the explicit modeling inherent in 3DGS introduces a gradient bias during optimization, rendering its non-convex optimization process highly susceptible to convergence toward local suboptimal solutions. This constitutes a fundamental limitation in 3DGS optimization, which we term the Blur Trap. To address this limitation, we integrate simple explicit exploration into the 3DGS optimization framework. First, through rigorous mathematical analysis of the 3DGS optimization formulation, we identify the underlying optimization bias responsible for the Blur Trap and categorize it into two distinct subtypes: the Far-Side Blur Trap and the Near-Side Blur Trap. Subsequently, we propose two highly straightforward exploration strategies (Random Seeding and Random Splitting) to mitigate the far-side and near-side blur traps, respectively. Experimental validation demonstrates that the incorporation of these exploration operators effectively and complementarily overcome the Blur Trap, achieving high-quality rendering performance across multiple datasets. Project page: https://chengbo-wang.github.io/ExploreGS/
