P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

15 Jul 2020  ·  Zehao Yu, Lei Jin, Shenghua Gao ·

This paper tackles the unsupervised depth estimation task in indoor environments. The task is extremely challenging because of the vast areas of non-texture regions in these scenes. These areas could overwhelm the optimization process in the commonly used unsupervised depth estimation framework proposed for outdoor environments. However, even when those regions are masked out, the performance is still unsatisfactory. In this paper, we argue that the poor performance suffers from the non-discriminative point-based matching. To this end, we propose P$^2$Net. We first extract points with large local gradients and adopt patches centered at each point as its representation. Multiview consistency loss is then defined over patches. This operation significantly improves the robustness of the network training. Furthermore, because those textureless regions in indoor scenes (e.g., wall, floor, roof, \etc) usually correspond to planar regions, we propose to leverage superpixels as a plane prior. We enforce the predicted depth to be well fitted by a plane within each superpixel. Extensive experiments on NYUv2 and ScanNet show that our P$^2$Net outperforms existing approaches by a large margin. Code is available at \url{https://github.com/svip-lab/Indoor-SfMLearner}.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Monocular Depth Estimation NYU-Depth V2 self-supervised P2Net+PP Root mean square error (RMSE) 0.553 # 5
Absolute relative error (AbsRel) 0.147 # 5
delta_1 80.4 # 5
delta_2 95.2 # 5
delta_3 98.7 # 5

Methods


No methods listed for this paper. Add relevant methods here