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

## TL;DR

This paper introduces an end-to-end, fully-convolutional method for aligning CAD models to 3D scans, improving accuracy by 19.04% and achieving significantly faster runtime compared to previous approaches.

## Contribution

It proposes a novel differentiable Procrustes alignment combined with symmetry-aware dense correspondence prediction for scene-level CAD model alignment.

## Key findings

- Outperforms state-of-the-art by 19.04% in alignment accuracy.
- Operates in a single forward pass, 250 times faster.
- Effectively aligns CAD models to complex 3D scans.

## Abstract

We present a novel, end-to-end approach to align CAD models to an 3D scan of a scene, enabling transformation of a noisy, incomplete 3D scan to a compact, CAD reconstruction with clean, complete object geometry. Our main contribution lies in formulating a differentiable Procrustes alignment that is paired with a symmetry-aware dense object correspondence prediction. To simultaneously align CAD models to all the objects of a scanned scene, our approach detects object locations, then predicts symmetry-aware dense object correspondences between scan and CAD geometry in a unified object space, as well as a nearest neighbor CAD model, both of which are then used to inform a differentiable Procrustes alignment. Our approach operates in a fully-convolutional fashion, enabling alignment of CAD models to the objects of a scan in a single forward pass. This enables our method to outperform state-of-the-art approaches by $19.04\%$ for CAD model alignment to scans, with $\approx 250\times$ faster runtime than previous data-driven approaches.