AI Paper Atlas

Research map / 3D vision / Depth and stereo

SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context

Shuyuan Lin, Hailiang Liao, Qiang Qi, Junjie Huang, Taotao Lai, Jian Weng

AAAI 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
add hierarchical encoder-decoder (HED) to the ConvMatch baseline (ablation)SC-Net baseline · YFCC100M known scenesmAP@5deg: 46.09 -> 57.96Improved
add the motion feature modulator (MFM) on top of HED (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 57.96 -> 59.60Improved
add soft filtering with previous-layer classification logits (AFR) (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 59.60 -> 61.96Improved
add position-aware attention (AFR) (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 61.96 -> 64.35Improved
use 6 rectifying layers instead of 4 (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 60.79 -> 64.35Improved
increase rectifying layers from 6 to 8 (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 64.35 -> 63.96Hurt
use grid size K=16 instead of K=12 (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 63.24 -> 64.35Improved
increase grid size from 16 to 20 (ablation)SC-Net · YFCC100M known scenesmAP@5deg: 64.35 -> 63.40Hurt
train on SIFT, test on SuperPoint matches with SC-Net instead of ConvMatch+correspondence pruning · YFCC100M SuperPoint (trained on SIFT)mAP@5deg: 30.85 -> 44.08Improved
SC-Net instead of best prior on outlier removalcorrespondence pruning · YFCC100M known scenesF-score: 79.87 -> 82.82Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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