AI Paper Atlas

Research map / 3D vision / Depth and stereo

SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings

Yuchen Wu, Jiahe Li, Xiaohan Yu, Lina Yu, Jin Zheng, Xiao Bai

CVPR 2026 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add basic scene coordinate branch (ablation)DPVO + DINOv3 · KITTI OdometryATE RMSE (m): 45.84 -> 43.62Improved
add geometry-guided scale propagation (geometry-modulated attention, reference selection, frame aggregation) (ablation)SCE-SLAM · KITTI OdometryATE RMSE (m): 43.62 -> 31.83Improved
use SuperPoint keypoint sampling instead of random sampling (ablation)SCE-SLAM · KITTI OdometryATE RMSE (m): 31.83 -> 25.79Improved
add loop closure (ablation)SCE-SLAM · KITTI OdometryATE RMSE (m): 25.79 -> 14.07Improved
use DINOv3 features (ablation)DPVO · KITTI OdometryATE RMSE (m): 53.61 -> 45.84Improved
use DINOv3 features (ablation)DPV-SLAM++ · KITTI OdometryATE RMSE (m): 25.75 -> 22.91Improved
replace DPVO with SCE-SLAM design, both with DINOv3 (ablation)DPVO + DINOv3 · KITTI OdometryATE RMSE (m): 45.84 -> 25.79Improved
SCE-SLAM vs DPV-SLAM++ both with loop closure and DINOv3 (ablation)SCE-SLAM · KITTI OdometryATE RMSE (m): 22.91 -> 14.07Improved
use scene coordinate embeddings instead of external metric depth (MegaSaM)SCE-SLAM · Waymo OpenATE RMSE (m): 2.776 -> 0.915Improved
SCE-SLAM vs DPV-SLAM++ with loop closureSCE-SLAM · Virtual KITTIATE RMSE (m): 0.343 -> 0.280Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy