cs.CVNov 12, 2026

Kosmo-GFM: A Production-Ready Geometry Foundation Model

Authors: Sheng Tang, Shengzhe Wei, Tiancheng Chen, Wenhua Jin, Xinyang Lu, Tinghao Jiang, Shuoxuan Feng, Yupeng Liu, 

Organizations: Kosmo Research

Abstract

We present Kosmo-GFM, a scene reconstruction system that integrates a geometry foundation model (GFM), a pose optimization engine (PoseEngine), and reconstruction-derived supervision from KosmoWorld. GFM predicts camera parameters, depth, cross-view correspondences, and dynamic 3D points from images and videos. PoseEngine combines these predictions with geometric optimization to recover scene-level camera poses and geometry for downstream 3D and 4D Gaussian Splatting. KosmoWorld generates images and geometric supervision from reconstructed real-world scenes to improve GFM's geometric predictions. On the Sparse and Medium subsets of SpatialBench, GFM achieves the lowest absolute relative depth error and the highest relative-pose AUC at 5 degrees among the compared methods. It also achieves the lowest mean endpoint errors for dynamic points and scene flow across the five evaluated datasets. Across 34 scenes completed by all compared reconstruction systems, PoseEngine achieves the highest scene-averaged pose AUC at thresholds of 1, 3, and 5 degrees, with a cumulative runtime of 14.07 hours, approximately 20% of GLUEMAP's 69.67 hours. PoseEngine Flash provides a further accuracy-efficiency trade-off, with a measured mixed-precision runtime of 2.62 hours, approximately 4% of GLUEMAP's runtime. Separate scaling experiments show generally favorable trends with increased data, model computation, and training budgets. These results support the use of learned geometric priors within a scene-level reconstruction pipeline.

Figures & tables

Explore similar work

CardsList
  1. Glob3R: Global Structure-from-Motion with 3D Foundation Models

    Jul 10, 2026Junyuan Deng, Heng Li, Kejie Qiu +7Bundle AdjustmentMulti-View 3D Reconstruction

  2. Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself

    Apr 15, 2026Yuhang Dai, Xingyi YangFeed-Forward 3D ReconstructionMulti-View 3D Reconstruction

  3. VG2\text{VG}^2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer

    Jun 1, 2026Yibin Zhao, Yihan Pan, Jun Nan +33D Gaussian SplattingNovel View Synthesis