基於離散化SDF的高斯濺射技術用於可重光照資產

Gaussian Splatting with Discretized SDF for Relightable Assets

July 21, 2025

作者: Zuo-Liang Zhu, Jian Yang, Beibei Wang

cs.AI

摘要

三維高斯濺射（3DGS）在新視角合成（NVS）任務中展現了其細膩的表達能力和高效的渲染速度。然而，在逆向渲染的應用中仍面臨諸多挑戰，因為高斯基元的離散特性使得幾何約束難以施加。近期研究引入了有符號距離場（SDF）作為額外的連續表示，以規範由高斯基元定義的幾何形狀，這雖然提升了分解質量，卻以增加記憶體使用和複雜化訓練為代價。與這些工作不同，我們提出了一種離散化的SDF，通過在每個高斯內部編碼採樣值來以離散方式表示連續SDF。這種方法使我們能夠通過SDF到不透明度的轉換將SDF與高斯不透明度相聯繫，從而實現通過濺射渲染SDF，避免了光線步進的計算成本。關鍵挑戰在於規範離散樣本與底層SDF的一致性，因為離散表示難以應用基於梯度的約束（如Eikonal損失）。為此，我們將高斯投影到SDF的零水平集上，並強制其與濺射產生的表面對齊，即基於投影的一致性損失。得益於離散化的SDF，我們的方法在無需額外記憶體（超越GS）且避免複雜手動設計優化的情況下，實現了更高的重光照質量。實驗表明，我們的方法優於現有的基於高斯的逆向渲染方法。我們的代碼可在https://github.com/NK-CS-ZZL/DiscretizedSDF獲取。

English

3D Gaussian splatting (3DGS) has shown its detailed expressive ability and highly efficient rendering speed in the novel view synthesis (NVS) task. The application to inverse rendering still faces several challenges, as the discrete nature of Gaussian primitives makes it difficult to apply geometry constraints. Recent works introduce the signed distance field (SDF) as an extra continuous representation to regularize the geometry defined by Gaussian primitives. It improves the decomposition quality, at the cost of increasing memory usage and complicating training. Unlike these works, we introduce a discretized SDF to represent the continuous SDF in a discrete manner by encoding it within each Gaussian using a sampled value. This approach allows us to link the SDF with the Gaussian opacity through an SDF-to-opacity transformation, enabling rendering the SDF via splatting and avoiding the computational cost of ray marching.The key challenge is to regularize the discrete samples to be consistent with the underlying SDF, as the discrete representation can hardly apply the gradient-based constraints (\eg Eikonal loss). For this, we project Gaussians onto the zero-level set of SDF and enforce alignment with the surface from splatting, namely a projection-based consistency loss. Thanks to the discretized SDF, our method achieves higher relighting quality, while requiring no extra memory beyond GS and avoiding complex manually designed optimization. The experiments reveal that our method outperforms existing Gaussian-based inverse rendering methods. Our code is available at https://github.com/NK-CS-ZZL/DiscretizedSDF.