FaDIV-Syn: Fast Depth-Independent View Synthesis

We introduce FaDIV-Syn, a fast depth-independent method for novel view synthesis. Related methods are often limited by their depth estimation stage, where incorrect depth predictions can lead to large projection errors. To avoid this issue, we efficiently warp input images into the target frame for a range of assumed depth planes. The resulting plane sweep volume (PSV) is directly fed into our network, which first estimates soft PSV masks in a self-supervised manner, and then directly produces the novel output view. We therefore side-step explicit depth estimation. This improves efficiency and performance on transparent, reflective, thin, and feature-less scene parts. FaDIV-Syn can perform both interpolation and extrapolation tasks and outperforms state-of-the-art extrapolation methods on the large-scale RealEstate10k dataset. In contrast to comparable methods, it achieves real-time performance due to its lightweight architecture. We thoroughly evaluate ablations, such as removing the Soft-Masking network, training from fewer examples as well as generalization to higher resolutions and stronger depth discretization.