SUFLECA shows NOC-based correspondence can improve CAD-to-image alignment

ducha_aiki · x · 2026-07-21

SUFLECA (“Scaling Up Feature Learning for CAD-to-image Alignment”) proposes a new way to train CAD-to-image alignment models.

The post’s TL;DR is that normalized object surface coordinates (NOCs) are a good proxy target for correspondence learning. The figures show the architecture: multi-scale features from a frozen perception encoder are fused with a Dense Prediction Transformer, then decoded by a lightweight binned NOC head to predict correspondences.

The paper also lists dataset composition and ablations:

Overall, the post argues that better correspondence modeling and CAD retrieval accuracy are central to alignment quality.

Original post →

More from Research

Research channel →