CVPR2025

MonSter: Marry Monodepth to Stereo Unleashes Power

Junda Cheng, Longliang Liu, Gangwei Xu, Xianqi Wang, Zhaoxing Zhang, Yong Deng, Jinliang Zang, Yurui Chen, Zhipeng Cai, Xin Yang

DOI Publisher

Abstract

Figure 1. Zero-shot generalization comparison: all models are trained on Scene Flow and tested directly on KITTI. Compared to the baseline IGEV [37], our method MonSter shows significant improvement in challenging regions such as reflective surfaces, textureless areas, fine structures, and distant objects.