Deep Upright Adjustment of 360 Panoramas Using Multiple Roll Estimations

Junho Jeon

Jinwoong Jung

Seungyong Lee

Asian Conference on Computer Vision (ACCV 2018), December 2018.


Misalignment of the orientations between a 360 camera and the scene results in a wavy and distorted spherical panorama image, which may look unstable and have poor perceptual quality. To automatically correct such mis-oriented 360 panoramas, this paper proposes a novel upright adjustment framework based on a convolutional neural network. Instead of directly predicting the 3D rotation of the camera on a given panorama image, our method estimates the rotation by analyzing the projected 2D rotations of multiple images sampled from the panorama. To accurately estimate the rotations of 2D sampled images, we train a 2D roll estimation network using a large-scale labeled image dataset generated by cropping 360 spherical panoramas with various view orientations. Experimental results demonstrate that the proposed method accurately and robustly handles upright adjustment of rotated panoramas while outperforming the previous methods on test datasets that consist of a variety of scenes.

PDF, 15.0MB
Test set (indoor)
ZIP, 4.63GB
Test set (street)
ZIP, 5.21GB
Test set (park)
ZIP, 7.25GB
Test set (mountain)
ZIP, 5.31GB
see the new features in coupe website [link]


title={Deep Upright Adjustment of 360 Panoramas Using Multiple Roll Estimations},
author={Jeon, Junho and Jung, Jinwoong and Lee, Seungyong},
booktitle={Asian Conference on Computer Vision},