Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images
This work addresses scene understanding in panoramic images for applications like VR and robotics, representing an incremental improvement over existing single-task methods.
The paper tackles the problem of geometric estimation from monocular 360° images by introducing a multi-task learning network that simultaneously estimates depth and surface normals, achieving state-of-the-art performance in both tasks with superior results in complex scenes.
Geometric estimation is required for scene understanding and analysis in panoramic 360° images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, especially when dealing with intricate textures or complex object surfaces. We introduce a novel multi-task learning (MTL) network that simultaneously estimates depth and surface normals from 360° images. Our first innovation is our MTL architecture, which enhances predictions for both tasks by integrating geometric information from depth and surface normal estimation, enabling a deeper understanding of 3D scene structure. Another innovation is our fusion module, which bridges the two tasks, allowing the network to learn shared representations that improve accuracy and robustness. Experimental results demonstrate that our MTL architecture significantly outperforms state-of-the-art methods in both depth and surface normal estimation, showing superior performance in complex and diverse scenes. Our model's effectiveness and generalizability, particularly in handling intricate surface textures, establish it as a new benchmark in 360° image geometric estimation. The code and model are available at \url{https://github.com/huangkun101230/360MTLGeometricEstimation}.