AI Paper Atlas

Research map / Point clouds / Registration and matching

UniCorrn: Unified Correspondence Transformer Across 2D and 3D

Prajnan Goswami, Tianye Ding, Feng Liu, Huaizu Jiang

CVPR 2026 · Point clouds › Registration and matching · approach: Learned feature-based registration · 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 vanilla attention with Gaussian attention (ablation)UniCorrn small model · MegaDepth-1500 (small-scale)AUC@5: 36.4 -> 37.3Improved
increase keypoint queries from 100 to 800 (ablation)UniCorrn small model · MegaDepth-1500 (small-scale)AUC@5: 37.3 -> 38.2Improved
use single-head attention (H=1) (ablation)UniCorrn small model · MegaDepth-1500 (small-scale)AUC@5: 38.2 -> 39.5Improved
add contrastive loss (ablation)UniCorrn small model · MegaDepth-1500 (small-scale)AUC@5: 39.5 -> 43.9Improved
add 4x feature upsampling (ablation)UniCorrn small model · MegaDepth-1500 (small-scale)AUC@5: 43.9 -> 48.5Improved
add auxiliary supervision on intermediate predictions (1 decoder layer) (ablation)UniCorrn small model · MegaDepth-1500AUC@5: 28.8 -> 47.7Improved
add auxiliary supervision on intermediate predictions (5 layers) (ablation)UniCorrn small model · MegaDepth-1500AUC@5: 48.5 -> 50.6Improved
add pseudo point cloud training data (ablation)UniCorrn · 7Scenes (2D-3D)registration recall: 15.4 -> 77.8Improved
add pseudo point cloud training data (ablation)UniCorrn · 3DLoMatch (3D-3D)registration recall: 73.2 -> 81.8Improved
replace regression with the dual-stream attention matching decoder (ablation)UniCorrn small model · MegaDepth (2D-2D)AUC@5: 0.2 -> 50.6Improved
replace global matching with the proposed decoder (ablation)UniCorrn small model · 7Scenes (2D-3D)registration recall: 75.8 -> 77.8Improved
train jointly on all tasks rather than a single task (ablation)UniCorrn · 7Scenes (2D-3D)registration recall: 67.7 -> 91.0Improved

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