The advent of neural and Gaussian-based radiance field methods have achieved
great success in the field of novel view synthesis. However, specular
reflection remains non-trivial, as the high frequency radiance field is
notoriously difficult to fit stably and accurately. We present a deferred
shading method to effectively render specular reflection with Gaussian
splatting. The key challenge comes from the environment map reflection model,
which requires accurate surface normal while simultaneously bottlenecks normal
estimation with discontinuous gradients. We leverage the per-pixel reflection
gradients generated by deferred shading to bridge the optimization process of
neighboring Gaussians, allowing nearly correct normal estimations to gradually
propagate and eventually spread over all reflective objects. Our method
significantly outperforms state-of-the-art techniques and concurrent work in
synthesizing high-quality specular reflection effects, demonstrating a
consistent improvement of peak signal-to-noise ratio (PSNR) for both synthetic
and real-world scenes, while running at a frame rate almost identical to
vanilla Gaussian splatting.

基于神经和高斯辐射场方法，在小说视角合成领域取得了巨大的成功。然而，镜面反射仍然非常复杂，因为高频辐射场非常难以稳定准确地拟合。我们提出了一种延迟着色方法来有效地渲染具有高斯分片的镜面反射。主要挑战来自环境映射反射模型，该模型要求精确的表面法线，同时在不连续梯度处瓶颈法线估计。我们利用延迟着色生成的每像素反射梯度来桥接邻域高斯优化过程，使几乎准确的法线估计逐渐传播并最终传播到所有反射物体。我们的方法在合成和真实场景中，显著优于最先进的技术和同时进行的工作，表现出峰值信噪比（PSNR）的一致提高，同时运行速度几乎与原始高斯分片相同。