[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
-
Updated
Sep 9, 2026 - JavaScript
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[ECCV 2026]Official implementation of the paper: "FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry"
Official implementation of "TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation". Single-step surface normal estimation for general scenes and transparent objects. Code and model weights will be released progressively.
To associate your repository with the monocular-geometry-estimation topic, visit your repo's landing page and select "manage topics."