OpenCodePapers

monocular-depth-estimation-on-nyuv2-relative-moge-protocol

Depth EstimationMonocular Depth Estimation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAbsReldelta1ModelNameReleaseDate
Modality Forcing for Scalable Spatial Generation✓ Link0.02520.989Modality Forcing (FLUX.2-klein-9B)2026-06-11
MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement✓ Link0.02620.987MoGe-3 (ViT-G)2026-07-20
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation0.02750.9861PointDiT-H2026-07-02
MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details✓ Link0.02890.986MoGe-22025-07-03
MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision0.02970.9860MoGe (zero-shot)2024-10-24
FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry✓ Link0.02970.987FoundationGeo-Base (extra data)2026-07-13