Abstract | ||
---|---|---|
Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity. We leverage this phenomenon to approximate the scene in a 360-degree image with (H)orizontal-planes and (V)ertical-planes. To this end, we propose an effective divide-and-conquer strategy that divides pixels based on their plane orientation estimation; then, the succeeding instance segmentation module conquers the task of planes clustering more easily in each plane orientation group. Besides, parameters of V-planes depend on camera yaw rotation, but translation-invariant CNNs are less aware of the yaw change. We thus propose a yaw-invariant V-planar reparameterization for CNNs to learn. We create a benchmark for indoor panorama planar reconstruction by extending existing 360 depth datasets with ground truth H&V-planes (referred to as "PanoH&V" dataset) and adopt state-of-the-art planar reconstruction methods to predict H&V-planes as our baselines. Our method outperforms the baselines by a large margin on the proposed dataset. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPR46437.2021.01118 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cheng Sun | 1 | 2 | 3.06 |
Chi-Wei Hsiao | 2 | 2 | 1.04 |
Ning-Hsu Wang | 3 | 0 | 0.34 |
Min Sun | 4 | 1083 | 59.15 |
Hwann-Tzong Chen | 5 | 826 | 52.13 |