LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference
This addresses the problem of generating realistic novel views from single images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles single-view view synthesis by regressing locally-learned planes from a single RGB image to generate novel views, achieving state-of-the-art results with an LPIPS reduction of 4.8%-9.0% and an RV reduction of 73.9%-83.5% compared to MINE.
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 combine with different disparity distributions of datasets and propose an occlusion-aware reprojection loss as a simple yet effective geometric supervision technique. We also introduce a self-attention mechanism to improve occlusion inference and present a Block-Sampling Self-Attention (BS-SA) module to address the problem of applying self-attention to large feature maps. We demonstrate the effectiveness of our approach and generate state-of-the-art results on different datasets. Compared to MINE, our approach has an LPIPS reduction of 4.8%-9.0% and an RV reduction of 73.9%-83.5%. We also evaluate the performance on real-world images and demonstrate the benefits.