AI RESEARCH

H-OmniStereo: Zero-Shot Omnidirectional Stereo Matching with Heading-Aligned Normal Priors

arXiv CS.CV

ArXi:2605.14963v1 Announce Type: new Stereo matching on top-bottom equirectangular images provides an effective framework for full-surround perception, as vertically aligned epipolar lines enable the use of advanced perspective stereo architectures that are largely driven by large-scale datasets and monocular priors. However, the performance of such adaptations is severely limited by the scarcity of omnidirectional stereo datasets and the degradation of perspective monocular priors under spherical distortions.