In this study, we present a method for synthesizing novel views from a single 360-degree RGB-D image based on the neural radiance field (NeRF) . Prior studies relied on the neighborhood interpolation capability of multi-layer perceptrons to complete missing regions caused by occlusion and zooming, which leads to artifacts. In the method proposed in this study, the input image is reprojected to 360-degree RGB images at other camera positions, the missing regions of the reprojected images are completed by a 2D image generative model, and the completed images are utilized to train the NeRF. Because multiple completed images contain inconsistencies in 3D, we introduce a method to learn the NeRF model using a subset of completed images that cover the target scene with less overlap of completed regions. The selection of such a subset of images can be attributed to the maximum weight independent set problem, which is solved through simulated annealing. Experiments demonstrated that the proposed method can synthesize plausible novel views while preserving the features of the scene for both artificial and real-world data.

翻译：在本研究中，我们提出了一种基于神经辐射场（NeRF）、从单张360度RGB-D图像合成新型视图的方法。以往研究依赖多层感知器的邻域插值能力来补全由遮挡和缩放造成的缺失区域，这会导致伪影。在本研究提出的方法中，输入图像被重投影至其他相机位置的360度RGB图像，缺失区域通过二维图像生成模型补全，并利用补全图像训练NeRF。由于多张补全图像在三维空间中存在不一致性，我们引入一种方法：通过选取覆盖目标场景且重叠区域较少的补全图像子集来学习NeRF模型。此类图像子集的选取可归结为最大权独立集问题，并通过模拟退火求解。实验表明，本方法能够在保留场景特征的同时，为人工与真实世界数据合成合理的新型视图。