LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference. (arXiv:2307.12217v2 [cs.CV] UPDATED)

We propose a novel method, LoLep, which regresses Locally-Learned planes from
a single RGB image to represent scenes accurately, thus generating better novel
views. Without the depth information, regressing appropriate plane locations is
a challenging problem. To solve this issue, we pre-partition the disparity
space into bins and design a disparity sampler to regress local offsets for
multiple planes in each bin. However, only using such a sampler makes the
network not convergent; we further propose two optimizing strategies that …

arxiv attention image inference information issue locations novel plane planes self-attention space synthesis