Lune

CVPR2025

HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation

Mehdi Zayene, Jannik Endres, Albias Havolli, Charles Corbière, Salim Cherkaoui, Alexandre Kontouli, Alexandre Alahi

DOI出版方

摘要

Figure 1. Examples from the HELVIPAD dataset in diverse settings (indoor, outdoor), under varied lighting (day, night). The dataset consists of paired top-bottom images with corresponding depth maps, captured from a robot navigating in dynamic human environments.