OmniFusion (2-iter)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Depth EstimationonStanford2D3D Panoramic
RMSE· 2022-03-02
0.3474
best: 0.2619 (HiMODE)
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion arXiv:2203.00838
Depth EstimationonStanford2D3D Panoramic
absolute relative error· 2022-03-02
0.095
best: 0.0405 (PanoFormer)
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion arXiv:2203.00838

Methodology2 results

3DonStanford2D3D Panoramic
RMSE· 2022-03-02
0.3474
best: 0.2619 (HiMODE)
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion arXiv:2203.00838
3DonStanford2D3D Panoramic
absolute relative error· 2022-03-02
0.095
best: 0.0405 (PanoFormer)
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion arXiv:2203.00838