AI Paper Atlas

Research map / 3D vision / Face and shape

FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos

Florian Maximilian Langer, Jihong Ju, Georgi Dikov, Gerhard Reitmayr, Mohsen Ghafoorian

ECCV 2024 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 11 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
predict front-facing side with a separate classification head instead of encoding orientation in embeddings (ablation)FastCAD · Scan2CAD (scan)instance alignment accuracy: 56.2 -> 60.1Improved
use symmetry-aware front-facing targets (ablation)FastCAD · Scan2CAD (scan)instance alignment accuracy: 60.1 -> 61.7Improved
distill CAD embeddings into the detector instead of cropping with predicted bbox and re-encoding (ablation)FastCAD · Scan2CAD reconstruction accuracy (scan)reconstruction accuracy: 15.6 -> 41.7Improved
distill embeddings versus two-step retrieval even with nearest GT bbox (ablation)FastCAD · Scan2CAD shape accuracy (scan)shape accuracy: 78.1 -> 83.1Improved
add Chamfer regression and segmentation auxiliary tasks to encoder training (ablation)FastCAD encoder · Scan2CAD reconstruction accuracy (scan)reconstruction accuracy: 38.3 -> 41.7Improved
add auxiliary tasks to encoder training on instance alignment accuracy (ablation)FastCAD encoder · Scan2CAD (scan)instance alignment accuracy: 62.3 -> 61.7No clear effect
use Perceiver encoder instead of PointNet++ (ablation)FastCAD encoder · Scan2CAD reconstruction accuracy (scan)reconstruction accuracy: 29.6 -> 38.3Improved
remove colour from scan input (ablation)FastCAD · Scan2CAD (scan)instance alignment accuracy: 61.7 -> 60.4No clear effect
reduce input points from 50K to 5K (ablation)FastCAD · Scan2CAD (scan)instance alignment accuracy: 61.7 -> 51.4Hurt
use FastCAD on reconstructed point cloud from video versus frame-based methodsFastCAD (Video) · Scan2CAD (video)instance alignment accuracy: 43.0 -> 48.2Improved
FastCAD versus ScanNotate on alignment (ScanNotate starts from GT poses)FastCAD (Scan) · Scan2CAD (scan)alignment accuracy: 78.2 -> 61.7Hurt
display class with inconsistent CAD orientation in ShapeNetFastCAD · Scan2CAD per-class (scan)display alignment accuracy: 24.1 vs mean 52.8Hurt

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