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.

翻译：神经辐射场与高斯辐射场方法的兴起，在新视角合成领域取得了巨大成功。然而，镜面反射的处理依然具有挑战性，因为高频辐射场的稳定精确拟合一直是个难题。本文提出了一种延迟着色方法，用于在高斯溅射中高效渲染镜面反射。核心挑战源于环境贴图反射模型，该模型既需要精确的表面法线，又因梯度不连续而阻碍了法线估计。我们利用延迟着色生成的逐像素反射梯度，桥接相邻高斯分布的优化过程，使得近乎正确的法线估计能够逐步传播，最终覆盖所有反射物体。本方法在合成高质量镜面反射效果方面显著优于现有最优技术与同期研究，在合成场景和真实场景中均实现了峰值信噪比（PSNR）的持续提升，同时保持了与原始高斯溅射几乎相同的帧率。