Humanoid-OmniOcc delivers a large-scale panoramic stereo occupancy dataset for humanoid robots via Real2Sim2Real, with a model that outperforms monocular baselines in both unseen sim scenes and real settings.
A sur- vey on deep stereo matching in the twenties
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Bi-CMPStereo uses bidirectional prompting to project event and frame data into each other's domains, creating aligned representations for improved cross-modal stereo matching.
citing papers explorer
-
Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI
Humanoid-OmniOcc delivers a large-scale panoramic stereo occupancy dataset for humanoid robots via Real2Sim2Real, with a model that outperforms monocular baselines in both unseen sim scenes and real settings.
-
Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
Bi-CMPStereo uses bidirectional prompting to project event and frame data into each other's domains, creating aligned representations for improved cross-modal stereo matching.