We present a method to efficiently generate 3D-aware high-resolution images that are view-consistent across multiple target views. The proposed multiplane neural radiance model, named GMNR, consists of a novel {\alpha}-guided view-dependent representation ({\alpha}-VdR) module for learning view-dependent information. The {\alpha}-VdR module, faciliated by an {\alpha}-guided pixel sampling technique, computes the view-dependent representation efficiently by learning viewing direction and position coefficients. Moreover, we propose a view-consistency loss to enforce photometric similarity across multiple views. The GMNR model can generate 3D-aware high-resolution images that are viewconsistent across multiple camera poses, while maintaining the computational efficiency in terms of both training and inference time. Experiments on three datasets demonstrate the effectiveness of the proposed modules, leading to favorable results in terms of both generation quality and inference time, compared to existing approaches. Our GMNR model generates 3D-aware images of 1024 X 1024 pixels with 17.6 FPS on a single V100. Code : https://github.com/VIROBO-15/GMNR

翻译：我们提出了一种高效生成三维感知高分辨率图像的方法，该图像在多个目标视角下具有视角一致性。所提出的多平面神经辐射模型（名为GMNR）包含一个新颖的α引导视角依赖表示模块（α-VdR），用于学习视角依赖信息。该α-VdR模块借助α引导像素采样技术，通过学习观察方向和位置系数，高效计算视角依赖表示。此外，我们提出了一种视角一致性损失，以强制多个视角间的光度相似性。GMNR模型能够生成三维感知的高分辨率图像，在多个相机姿态下保持视角一致性，同时在训练和推理时间上均保持计算效率。在三个数据集上的实验证明了所提出模块的有效性，相较于现有方法，在生成质量和推理时间方面均取得了优越结果。我们的GMNR模型在单个V100 GPU上能以17.6 FPS生成1024×1024像素的三维感知图像。代码地址：https://github.com/VIROBO-15/GMNR