MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Benchmark Model Rank Results
monocular-depth-estimation-on-diode-relative-moge-protocolMoGe (zero-shot)–delta1: 0.9760AbsRel: 0.0313
monocular-depth-estimation-on-eth3d-relative-moge-protocolMoGe (zero-shot)–delta1: 0.9920AbsRel: 0.0271
monocular-depth-estimation-on-kitti-relative-moge-protocolMoGe (zero-shot)–delta1: 0.9800AbsRel: 0.0395
monocular-depth-estimation-on-nyuv2-relative-moge-protocolMoGe (zero-shot)–AbsRel: 0.0297delta1: 0.9860