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在多个目标视角下保持视角一致性的三维感知高分辨率图像的方法。所提出的多平面神经辐射模型(GMNR)包括一个称为{\alpha}-guided view-dependent representation ({\alpha}-Vdr)的新型模块,用于学习视角相关信息。{\alpha}-Vdr模块,通过{\alpha}-guided像素采样技术的支持,通过学习视角方向和位置系数,有效计算视角相关表示。此外,我们提出了一种视野一致性损耗函数,以在多个视角之间强制执行光度学相似性。GMNR模型能够在维持训练和推理时间的计算效率的同时,生成在多个相机姿态下保持视角一致性的三维感知高分辨率图像。在三个数据集上的实验表明了所提出模块的有效性,相比现有方法,生成质量和推理时间均优良。我们的GMNR模型在单个V100上以17.6 FPS生成1024x1024像素的三维感知图像。代码:https://github.com/VIROBO-15/GMNR