解决输入视角变化时渲染过亮和高分辨率下孔洞问题
RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering
- 通过α归一化保持不同输入视角下的亮度一致
- 引入基于3D采样的正则项提升高斯尺度估计精度
- 适合需要多视角泛化和高清渲染的应用场景
通用3D高斯点阵最近成为一种高效的新视角合成方法，可仅用少量输入视图实现前馈合成。然而，现有像素级前馈方法在推理时输入视图数量变化会导致渲染过亮，且缺乏对高斯尺度估计的充分监督，从而在高分辨率渲染中产生孔洞伪影。为此，我们发现过亮源于重叠高斯数量的变化，提出简单的alpha归一化策略以维持亮度一致性；同时引入基于3D采样的辅助正则项，提升高斯尺度估计，有效缓解高分辨率下的孔洞问题。在基准数据集上的实验表明，该方法在不同输入视图数量和高分辨率渲染设置下显著优于基线模型。
原文摘要 · Abstract (English)
Generalizable 3D Gaussian Splatting has recently emerged as an efficient approach for novel-view synthesis, enabling feed-forward synthesis from only a few input views. However, existing pixel-wise feed-forward methods suffer from over-bright renderings when the number of input views varies during inference, as well as insufficient supervision for accurate Gaussian scale estimation, which leads to hole artifacts, particularly in high-resolution renderings. To address these issues, we identify that the over-brightness is caused by the varying number of overlapping Gaussians and propose a simple alpha normalization strategy to maintain brightness consistency across different number of input views. In addition, we introduce an auxiliary 3D sampling-based regularizer to improve Gaussian scale estimation, thereby mitigating hole artifacts in high-resolution rendering. Experiments on benchmark datasets demonstrate that our method significantly improves baseline models under varying input-view and high-resolution rendering settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。