← Search

Xiaohuan Ding

2 accepted papers

2023

FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

ICCV 2023poster

Curvilinear object segmentation is critical for many applications. However, manually annotating curvilinear objects is very time-consuming and error-prone, yielding insufficiently available annotated datasets for existing supervised methods and domain adaptation methods. This paper proposes a self-s…

Cited by 12PDFcodeScholar
2023

Iterative Geometry Encoding Volume for Stereo Matching

CVPR 2023poster

Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties tackling local ambiguities in ill-posed regions. In this paper, we propose Iterative Geometry Encoding Volume (IGEV-Stereo…