Qi Feng, Hubert P. H. Shum, Ryo Shimamura, Shigeo Morishima
Foreground-aware Dense Depth Estimation for 360 Images
International Conferences in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG)
With 360 imaging devices becoming widely accessible, omnidirectional content has gained popularity in multiple fields. The ability to estimate depth from a single omnidirectional image can benefit applications such as robotics navigation and virtual reality 베가스 11 다운로드. However, existing depth estimation approaches produce sub-optimal results on real-world omnidirectional images with dynamic foreground objects. On the one hand, capture-based methods cannot obtain the foreground due to the limitations of the scanning and stitching schemes 프렌즈 시즌1. On the other hand, it is
challenging for synthesis-based methods to generate highly-realistic virtual foreground objects that are comparable to the real-world ones Download Legacy into the Future. In this paper, we propose to augment datasets with realistic foreground objects using an
image-based approach, which produces a foreground-aware photorealistic dataset for machine learning algorithms 수세 리눅스. By exploiting a novel scale-invariant RGB-D correspondence in the spherical domain, we repurpose abundant
non-omnidirectional datasets to include realistic foreground objects with correct distortions 명량해전 다운로드. We further propose a novel auxiliary deep neural network to estimate both the depth of the omnidirectional images and the mask of the foreground objects, where the two tasks facilitate each other Automatic download of Synology. A new local depth loss considers small regions of interest and ensures that their depth estimations are not smoothed out during the global gradient’s optimization 기술자들 다운로드. We demonstrate the system using human as the foreground due to its complexity and contextual importance, while the framework can be generalized to any other foreground objects Download from mac. Experimental results demonstrate more consistent global estimations and more accurate local estimations compared with state-of-the-arts.