AI Paper Atlas

Research map / 3D vision / Face and shape

MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts

Jingnan Gao, Zhe Wang, Xianze Fang, Xingyu Ren, Zhuo Chen, Shengqi Liu, Yuhao Cheng, Jiangjing Lyu, Xiaokang Yang, Yichao Yan

CVPR 2026 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 16 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 MoE layers (ablation)MoRE (VGGT-based) · DTU pointmapAccuracy (mean, lower better): 1.297 -> 1.011Improved
add MoE layers (ablation)MoRE (VGGT-based) · NYUv2 depthAbs Rel: 0.054 -> 0.051Improved
add MoE layers (ablation)MoRE (VGGT-based) · RealEstate10KAUC@30: 85.14 -> 86.28Improved
add tailored losses incl. confidence-based depth refinement (without MoE) (ablation)VGGT baseline · RealEstate10KAUC@30: 77.62 -> 85.14Improved
add tailored losses incl. confidence-based depth refinement (without MoE) (ablation)VGGT baseline · DTU pointmapCompletion (lower better): 1.896 -> 1.625Improved
add tailored losses (without MoE) (ablation)VGGT baseline · RealEstate10KRRA@30: 99.97 -> 99.94No clear effect
MoRE vs Pi3 on ETH3D pointmap accuracyMoRE · ETH3D pointmapAccuracy (mean): 0.194 (Pi3) vs 0.234 (MoRE)Hurt
MoRE vs monocular models on Sintel depthMoRE · Sintel depthAbs Rel: 0.273 (MoGe) vs 0.274No clear effect
add dense semantic (DINOv2) feature fusion for normal head (ablation)MoRE · Normal estimationqualitative sharpnessImproved
MoRE vs Pi3 on Co3Dv2 camera poseMoRE · Co3Dv2AUC@30: 88.42 vs 88.41 (Pi3), 88.59 (VGGT)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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