We propose LIRF (Local Implicit Ray Function), a generalizable neural rendering approach for novel view rendering. Current generalizable neural radiance fields (NeRF) methods sample a scene with a single ray per pixel and may therefore render blurred or aliased views when the input views and rendered views capture scene content with different resolutions. To solve this problem, we propose LIRF to aggregate the information from conical frustums to construct a ray. Given 3D positions within conical frustums, LIRF takes 3D coordinates and the features of conical frustums as inputs and predicts a local volumetric radiance field. Since the coordinates are continuous, LIRF renders high-quality novel views at a continuously-valued scale via volume rendering. Besides, we predict the visible weights for each input view via transformer-based feature matching to improve the performance in occluded areas. Experimental results on real-world scenes validate that our method outperforms state-of-the-art methods on novel view rendering of unseen scenes at arbitrary scales.

翻译：我们提出LIRF（局部隐式射线函数），一种用于新视角渲染的可泛化神经绘制方法。当前可泛化神经辐射场（NeRF）方法逐像素使用单条射线采样场景，当输入视角与渲染视角以不同分辨率捕捉场景内容时，可能导致绘制结果模糊或出现锯齿。为解决此问题，我们提出LIRF，通过聚合圆锥平截头体信息构建射线。给定圆锥平截头体内的三维位置，LIRF将三维坐标与圆锥平截头体特征作为输入，预测局部体积辐射场。由于坐标具有连续性，LIRF通过体积渲染连续尺度值的高质量新视角。此外，我们通过基于Transformer的特征匹配预测每个输入视角的可见权重，以提升遮挡区域的性能。在真实场景上的实验结果验证，本方法在任意尺度下对未见场景的新视角渲染中优于现有最先进方法。