RoSplat：用于变化输入视角和高分辨率渲染的鲁棒前馈像素级高斯散射
RoSplat: Robust Feed-Forward Pixel-wise Gaussian Splatting for Varying Input Views and High-Resolution Rendering
- Australian National University（澳大利亚国立大学）
- NVIDIA
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出RoSplat，通过引入alpha归一化策略和辅助3D采样正则化器，解决高斯散射在不同输入视角下的过亮问题和高分辨率渲染中的孔洞 artifacts，提升渲染质量。
AI中文摘要：
通用化的3D高斯散射最近在新型视角合成中作为一种高效方法出现，使仅需少量输入视角即可实现前馈合成。然而，现有的像素级前馈方法在推理过程中由于输入视角数量的变化导致过亮渲染，且缺乏对高斯尺度估计的充分监督，从而产生孔洞 artifacts，特别是在高分辨率渲染中更为明显。为了解决这些问题，我们发现过亮是由于重叠高斯数量的变化引起的，并提出一种简单的alpha归一化策略以在不同输入视角数量下保持亮度一致性。此外，我们引入了基于辅助3D采样的正则化器来改进高斯尺度估计，从而减轻高分辨率渲染中的孔洞 artifacts。在基准数据集上的实验表明，我们的方法在不同输入视角和高分辨率渲染设置下显著提升了基线模型的性能。
英文摘要：
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.
