AI Paper Atlas

Research map / 3D vision / Face and shape

End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans

Armen Avetisyan, Angela Dai, Matthias Niessner

ICCV 2019 · 3D vision › Face and shape · approach: Optimization-based shape matching · 80 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 differentiable Procrustes alignment loss (ablation)end-to-end CAD alignment · Scan2CAD valalignment accuracy (%): 35.74 -> 50.72Improved
add Procrustes loss versus direct 9DoF l2 regression (ablation)end-to-end CAD alignment · Scan2CAD valalignment accuracy (%): 15.12 -> 50.72Improved
add symmetry-aware dense correspondence (CORRS) prediction (ablation)end-to-end CAD alignment · Scan2CAD valalignment accuracy (%): 29.97 -> 50.72Improved
add explicit symmetry classification (ablation)CORRS prediction · Scan2CAD valalignment accuracy (%): 40.51 -> 50.72Improved
add anchor-style bounding box regression for object detection (ablation)end-to-end CAD alignment · Scan2CAD valalignment accuracy (%): 47.64 -> 50.72Mixed
add anchors (bounding boxes), class-average metric (ablation)end-to-end CAD alignment · Scan2CAD valclass avg alignment accuracy (%): 42.37 -> 44.61Improved
add Procrustes loss (ablation)end-to-end CAD alignment · SUNCG (synthetic scans)alignment accuracy (%): 36.42 -> 41.83Improved
end-to-end learned alignment versus decoupled correspondence + RANSACOurs vs Scan2CAD · Scan2CAD valalignment accuracy (%): 31.68 -> 50.72Improved
end-to-end single forward pass versus Scan2CAD optimizationOurs vs Scan2CAD · runtime, large sceneruntime (s): 740.34s -> 2.60sImproved
end-to-end method on hidden benchmark test setOurs vs Scan2CAD · Scan2CAD hidden test setalignment accuracy (%): 28.8 -> 44.1Improved

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