[2205.11733] Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images

arxiv.org · 6,269 words · saved by 1 readers

This paper deals with the challenging task of synthesizing novel views for in-the-wild photographs. Existing methods have shown promising results leveraging monocular depth estimation and color inpainting with layered depth representations. However, these methods still have limited capability to handle scenes with complex 3D geometry. We propose a new method based on the multiplane image (MPI) representation. To accommodate diverse scene layouts in the wild and tackle the difficulty in producing high-dimensional MPI contents, we design a network structure that consists of two novel modules, one for plane depth adjustment and another for depth-aware color prediction. The former adjusts the initial plane positions using the RGBD context feature and an attention mechanism. Given adjusted depth values, the latter predicts the color and density for each plane separately with proper inter-plane interactions achieved via a feature masking strategy. To train our method, we construct large-scale stereo training data using only unconstrained single-view image collections by a simple yet effective warp-back strategy. The experiments on both synthetic and real datasets demonstrate that our trained model works remarkably well and achieves state-of-the-art results.

Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images Yuxuan Han∗ Ruicheng Wang∗ Jiaolong Yang Tsinghua University USTC Microsoft Research Asia Beijing, China…

[2205.11733] Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images

related reading