Useg-PanoDepth:Unified 360° Depth Estimation for Indoor and Outdoor Scenes with Semantic Assistance

In complex 360∘ scenes, depth estimation is challenging for small objects and the depth of object boundaries, which cannot be effectively solved with existing works. 360∘ depth estimation is unable to produce uniform depth estimate findings in both indoor and outdoor settings due to the datasets. In this paper, the Useg-PanoDepth and PanoDepth dataset is proposed to improve the above problems effectively. The Diagonal-aware Attention Module (DAM) effectively estimates small objects in complex scenes. Enhanced Boundary Module (EBM), for enhancing boundary information,can also effectively solve the problem of depth unification of indoor and outdoor scenes. Extensive experiments on our constructed PanoDepth dataset, Useg-PanoDepth achieves SOTA results. The Relative accuracy (delta <1.25) reaches 87.82%. Following is the link to the source code at https://github.com/xjh6/Useg-PanoDepth.