AI Paper Atlas

Research map / 3D vision / 3D generation

Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space

Yingping Liang, Yutao Hu, Wenqi Shao, Ying Fu

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 4 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 3D-aware encoder (Stage 1) (ablation)L2M · ZEB GL3AUC@5: 50.2 -> 51.5Improved
add 3D-aware encoder (Stage 1) (ablation)L2M · ZEB BLEAUC@5: 41.6 -> 46.0Improved
add 3D-aware encoder (Stage 1) (ablation)L2M · ZEB SCEAUC@5: 34.4 -> 38.5Improved
add 3D-aware encoder (Stage 1) (ablation)L2M · ZEB MULAUC@5: 61.9 -> 61.7Hurt
train decoder on large-scale synthetic data (Stage 2) instead of MegaDepth only (ablation)L2M · ZEB GL3AUC@5: 46.0 -> 50.2Improved
train decoder on large-scale synthetic data (Stage 2) instead of MegaDepth only (ablation)L2M · ZEB ETOAUC@5: 77.2 -> 83.6Improved
L2M vs RoMa (outdoor) on zero-shot benchmarkL2M · ZEB meanAUC@5: 48.8 -> 51.8Improved
L2M vs RoMa on cross-modal RGB-IRL2M · METU-VisTIRAUC@5: 25.61 -> 30.13Improved
L2M vs RoMa after fine-tuning on MegaDepthL2M · MegaDepth-1500AUC@5: 62.6 -> 63.1Improved

Earlier methods this paper compares with

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