DReSS-D
收藏IEEE2026-04-17 收录
官方服务：
资源简介：
A fine-grained geo-tagged CVL dataset, DReSS-D, is introduced to provide pixel-level ground truth labels for training models. Each ground panoramic image is paired with a depth map, enabling every pixel in the query image to be projected into the reference image space.
提供机构：
Yi Wan
