AI Paper Atlas

Research map / 3D vision / Depth and stereo

Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation

Gongshu Wang, Zhirui Wang, Kan Yang

ECCV 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 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 LFR moduleDINOv3-B · NYU Depth v2AbsRel: 0.072 -> 0.070Improved
add LFR moduleDINOv3-L · NYU Depth v2AbsRel: 0.060 -> 0.057Improved
add LFR moduleDINOv3-B · KITTI (Eigen split)AbsRel: 0.057 -> 0.049Improved
add LFR moduleDINOv3-L · KITTI (Eigen split)AbsRel: 0.046 -> 0.043Improved
add LFR moduleDINOv3-L · SUN RGB-D (zero-shot from NYU)AbsRel: 0.101 -> 0.099Improved
add LFR moduleDINOv3-L · Argoverse (zero-shot from KITTI)AbsRel: 0.219 -> 0.204Improved
use last layer only instead of uniformly sampled layers (ablation)DINOv3-L + DPT · KITTI (Eigen split, ablation)AbsRel: 0.046 -> 0.045Improved
add recombination of selected intermediate layers (ablation)DINOv3-L + DPT · KITTI (Eigen split, ablation)AbsRel: 0.045 -> 0.043Improved
add recombination of selected intermediate layers (ablation)DINOv3-L + DPT · KITTI (Eigen split, ablation)RMSE: 1.743 -> 1.721Improved
add hierarchical normalization loss (ablation)DINOv3-L + LFR · KITTI (Eigen split, ablation)SIlog: 0.060 -> 0.059Improved
add multi-level weighted prediction (ablation)DINOv3-L + LFR · KITTI (Eigen split, ablation)RMSE: 1.719 -> 1.711Improved
select auxiliary layers by minimal similarity instead of predicted scores (ablation)LFR · KITTI (Eigen split, ablation)AbsRel: 0.044 -> 0.043Improved

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