360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images
This addresses geometric consistency issues in 360-degree image reconstruction for applications like VR and AR, but appears incremental as it builds on existing MVS methods with specific enhancements for distortion mitigation.
The paper tackles the problem of 3D reconstruction from 360-degree images, which suffer from distortion affecting feature extraction and geometric consistency, by proposing 360Recon, an MVS algorithm that uses spherical feature extraction and multi-scale enhanced features to achieve state-of-the-art performance in depth estimation and reconstruction on public datasets.
360-degree images offer a significantly wider field of view compared to traditional pinhole cameras, enabling sparse sampling and dense 3D reconstruction in low-texture environments. This makes them crucial for applications in VR, AR, and related fields. However, the inherent distortion caused by the wide field of view affects feature extraction and matching, leading to geometric consistency issues in subsequent multi-view reconstruction. In this work, we propose 360Recon, an innovative MVS algorithm for ERP images. The proposed spherical feature extraction module effectively mitigates distortion effects, and by combining the constructed 3D cost volume with multi-scale enhanced features from ERP images, our approach achieves high-precision scene reconstruction while preserving local geometric consistency. Experimental results demonstrate that 360Recon achieves state-of-the-art performance and high efficiency in depth estimation and 3D reconstruction on existing public panoramic reconstruction datasets.