AI Paper Atlas

Research map / 3D vision / Depth and stereo

Reliev3R: Relieving Feed-forward 3D Reconstruction from Multi-View Geometric Annotations

Youyu Chen, Junjun Jiang, Yueru Luo, Kui Jiang, Xianming Liu, Xu Yan, Dave Zhenyu Chen

CVPR 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo

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
train with weak supervision (monocular depth + correspondences) instead of full multi-view geometric annotationspi3-based FFRM trained on DL3DV-10K · DL3DV-benchmark 8-viewpoint map rel: 0.057 -> 0.122Hurt
Reliev3R weak supervision versus the weakly supervised AnyCamReliev3R · DL3DV-benchmark 8-viewcamera AUC@30: 29.527 -> 49.426Improved
Reliev3R weak supervision versus fully supervised early FFRM FLAREReliev3R · DL3DV-benchmark 8-viewpoint map rel: 0.134 -> 0.122Improved
weak supervision instead of full supervision, zero-shotpi3-based FFRM · ScanNet++ zero-shotdepth rel: 0.220 -> 0.124Improved
weak supervision instead of full supervision, zero-shotpi3-based FFRM · ScanNet++ zero-shotcamera AUC@30: 17.789 -> 15.711No clear effect
finetune a synthetic-pretrained model with Reliev3R weak supervision on real DL3DVpi3 pretrained on synthetic data · DL3DV-benchmark 8-viewdepth rel: 0.208 -> 0.106Improved
set confidence weight alpha to 1.0 instead of 0.2 (ablation)ambiguity-aware depth loss · DL3DV-benchmark 8-viewcamera AUC@30: 42.116 -> 49.426Improved
increase alpha from 1.0 to 2.0 (ablation)ambiguity-aware depth loss · DL3DV-benchmark 8-viewpoint map rel: 0.122 -> 0.127No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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