Distortion-Tolerant Monocular Depth Estimation On Omnidirectional Images Using Dual-cubemap
This work addresses a domain-specific problem for computer vision applications involving omnidirectional imagery, offering an incremental improvement by reducing distortion impact.
The paper tackles the challenge of depth estimation in omnidirectional images, which suffer from distortion that twists object shapes, by proposing a distortion-tolerant algorithm using a dual-cubemap approach, achieving superior performance over state-of-the-art methods.
Estimating the depth of omnidirectional images is more challenging than that of normal field-of-view (NFoV) images because the varying distortion can significantly twist an object's shape. The existing methods suffer from troublesome distortion while estimating the depth of omnidirectional images, leading to inferior performance. To reduce the negative impact of the distortion influence, we propose a distortion-tolerant omnidirectional depth estimation algorithm using a dual-cubemap. It comprises two modules: Dual-Cubemap Depth Estimation (DCDE) module and Boundary Revision (BR) module. In DCDE module, we present a rotation-based dual-cubemap model to estimate the accurate NFoV depth, reducing the distortion at the cost of boundary discontinuity on omnidirectional depths. Then a boundary revision module is designed to smooth the discontinuous boundaries, which contributes to the precise and visually continuous omnidirectional depths. Extensive experiments demonstrate the superiority of our method over other state-of-the-art solutions.