novel view synthesis from a single image has recently achieved remarkable
results, although the requirement of some form of 3D, pose, or multi-view
supervision at training time limits the deployment in real scenarios. This work
aims at relaxing these assumptions enabling training of co
本文提出了一种使用真实图像来训练、无需 3D 场景真值信息，通过可微分点云渲染器将潜在 3D 特征点云转换为目标视图输出图像，并通过细化网络解码来填补缺失区域的新型端到端模型，在测试时可以对潜在特征空间进行可解释的操作，可以生成高分辨率图像并推广到其他输入分辨率，将在 Matterport、Replica 和 RealEstate10K 数据集上优于基线和之前的工作。