MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors

ArXi:2602.05330v2 Announce Type: replace Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolution, multi-task annotations. While perspective foundation models have achieved success through data scaling, directly adapting them to the panoramic domain often fails due to severe geometric distortions and coordinate system discrepancies. Furthermore, the underlying relations between diverse dense prediction tasks in spherical spaces are underexplored.