Neural Radiance Field (NeRF) has revolutionized free viewpoint rendering tasks and achieved impressive results. However, the efficiency and accuracy problems hinder its wide applications. To address these issues, we propose Geometry-Aware Generalized Neural Radiance Field (GARF) with a geometry-aware dynamic sampling (GADS) strategy to perform real-time novel view rendering and unsupervised depth estimation on unseen scenes without per-scene optimization. Distinct from most existing generalized NeRFs, our framework infers the unseen scenes on both pixel-scale and geometry-scale with only a few input images. More specifically, our method learns common attributes of novel-view synthesis by an encoder-decoder structure and a point-level learnable multi-view feature fusion module which helps avoid occlusion. To preserve scene characteristics in the generalized model, we introduce an unsupervised depth estimation module to derive the coarse geometry, narrow down the ray sampling interval to proximity space of the estimated surface and sample in expectation maximum position, constituting Geometry-Aware Dynamic Sampling strategy (GADS). Moreover, we introduce a Multi-level Semantic Consistency loss (MSC) to assist more informative representation learning. Extensive experiments on indoor and outdoor datasets show that comparing with state-of-the-art generalized NeRF methods, GARF reduces samples by more than 25\%, while improving rendering quality and 3D geometry estimation.

翻译：神经光度场( NERF) 革命了自由观点的革命性,赋予了任务,并取得了令人印象深刻的成果。然而,效率和精确度问题阻碍了它的广泛应用。为了解决这些问题,我们提议了具有几何-内存通用神经光度场(GARF)的几何-内存通用神经光度场(GARF)战略,以进行实时新颖的视图显示和未经监督的深度估计,而没有按部就班地优化。与大多数现有的通用 NERF不同,我们的框架将像素尺度和几何尺度的无形场景都推断成像级和几何几何尺度,只有很少的输入图像。更具体地说,我们的方法通过编码-脱coder(GARF)结构来学习新观点合成的通用神经光度,以及有助于避免隐蔽的点级多视角特征融合模块。为了在通用模型中保存场景特征,我们引入了一种非超强的深度估计模型,将光谱采样间隔间隔缩小到预期最高位置的表面和样本空间的近处,这构成了大地测量-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内存-内化-比较战略(GD-更有助于-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-更能化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内化-内