AI Paper Atlas

Research map / 3D vision / Depth and stereo

Boosting Correspondence Learning with Structure-Aware Estimator

Tianyu Yan, Wei An, Pu Wang, Yingqian Wang

ECCV 2026 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 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
replace weighted eight-point WLS with structure-aware estimatorDeMatch++ · YFCC100M relative poseAUC@5deg: 34.33 -> 40.03Improved
replace WLS with structure-aware estimatorConvMatch · YFCC100M relative poseAUC@5deg: 26.78 -> 32.44Improved
replace WLS with structure-aware estimatorDeMatch · YFCC100M relative poseinference time (ms): 10.155 -> 11.413Hurt
replace WLS with structure-aware estimatorUMatch/DeMatch/DeMatch++/ConvMatch · HPatches homographyaccuracy at @1px..@10px: @3px: DeMatch++ 49.66 -> 55.34; @1px ConvMatch -1.03; @10px DeMatch -2.41Mixed
replace WLS with structure-aware estimatorDeMatch · Aachen Day-Night v1.1 nightlocalized queries (%): 53.4 -> 57.1 (0.25m,2deg)Improved
replace WLS with structure-aware estimatorDeMatch · Aachen Day-Night v1.1 daylocalized queries (%): 85.9 -> 86.0No clear effect
replace WLS with structure-aware estimatorOANet · Line fitting, outlier ratioL2 error: 60%: 0.0254 -> 0.0260; 95%: 0.2720 -> 0.2381Mixed
replace WLS with structure-aware estimator, zero-shot indoor transferConvMatch/UMatch/DeMatch/DeMo/DeMatch++ · YFCC100M to SUN3D (zero-shot)AUC@5deg: ConvMatch SIFT 2.17 -> 2.07; UMatch 2.28 -> 2.56Mixed
fine-tune estimator on small SUN3D subset (few-shot)structure-aware estimator · SUN3D few-shotAUC@5deg: ConvMatch SIFT 2.49 -> 3.53Improved
add graph Laplacian operation (ablation)DeMatch with structure-aware estimator · YFCC100MAUC@5deg: 30.52 -> 36.58Improved
add degree matrix D (ablation)DeMatch with structure-aware estimator · YFCC100MAUC@5deg: 33.92 -> 36.58Improved
add learnable regularization scalar alpha (ablation)DeMatch with structure-aware estimator · YFCC100MAUC@5deg: 36.04 -> 36.58Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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