GPS-Gaussian：通用像素級3D高斯飛濺技術用於實時人體新視角合成

摘要

我們提出了一種新方法，稱為GPS-Gaussian，用於以實時方式合成角色的新視圖。所提出的方法在稀疏視圖相機設置下實現了2K分辨率渲染。與原始的高斯飛灰或神經隱式渲染方法不同，這些方法需要對每個主題進行優化，我們引入了在源視圖上定義的高斯參數圖，並直接回歸高斯飛灰屬性，以便即時合成新視圖，而無需進行任何微調或優化。為此，我們在大量人體掃描數據上訓練我們的高斯參數回歸模塊，同時還有一個深度估計模塊，將2D參數圖提升到3D空間。所提出的框架是完全可微的，對幾個數據集進行的實驗表明，我們的方法優於最先進的方法，同時實現了超越的渲染速度。

English

We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian Splatting or neural implicit rendering methods that necessitate per-subject optimizations, we introduce Gaussian parameter maps defined on the source views and regress directly Gaussian Splatting properties for instant novel view synthesis without any fine-tuning or optimization. To this end, we train our Gaussian parameter regression module on a large amount of human scan data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable and experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.

GPS-Gaussian：通用像素級3D高斯飛濺技術用於實時人體新視角合成

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

摘要

Support