S-OmniMVS: Incorporating sphere geometry into omnidirectional stereo matching

Z Chen, C Lin, L Nie, Z Shen, K Liao, Y Cao… - Proceedings of the 31st …, 2023 - dl.acm.org
Multi-fisheye stereo matching is a promising task that employs the traditional multi-view
stereo (MVS) pipeline with spherical swee** to acquire omnidirectional depth. However …

Geometry-Aware Self-Supervised Indoor 360° Depth Estimation via Asymmetric Dual-Domain Collaborative Learning

X Wang, Z He, Q Zhang, Y Yang… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Being able to estimate monocular depth for spherical panoramas is of fundamental
importance in 3D scene perception. However, spherical distortion severely limits the …

CasOmniMVS: Cascade Omnidirectional Depth Estimation with Dynamic Spherical Swee**

P Wang, M Li, J Cao, S Du, Y Li - Applied Sciences, 2024 - mdpi.com
Estimating 360∘ depth from multiple cameras has been a challenging problem. However,
existing methods often adopt a fixed-step spherical swee** approach with densely …

Real-time Multi-view Omnidirectional Depth Estimation System for Robots and Autonomous Driving on Real Scenes

M Li, X Yang, C Wu, J Li, P Wang, X Hu, S Du… - arxiv preprint arxiv …, 2024 - arxiv.org
Omnidirectional Depth Estimation has broad application prospects in fields such as robotic
navigation and autonomous driving. In this paper, we propose a robotic prototype system …

Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images

C Pulling, JH Tan, Y Hu, S Scherer - arxiv preprint arxiv:2405.05355, 2024 - arxiv.org
Multi-view stereo omnidirectional distance estimation usually needs to build a cost volume
with many hypothetical distance candidates. The cost volume building process is often …