Scan2CAD: Learning CAD Model Alignment in RGB-D Scans

TL;DR

Scan2CAD introduces a data-driven approach that aligns CAD models to noisy RGB-D scans by learning keypoint correspondences with a novel 3D CNN, significantly improving alignment accuracy.

Contribution

The paper presents a new dataset, a novel 3D CNN architecture for joint embedding, and a variational energy minimization method for CAD alignment in RGB-D scans.

Findings

Outperforms previous methods by 21.39% on the Scan2CAD benchmark.

Creates a large annotated dataset with 97,607 keypoint pairs.

Demonstrates effective alignment of CAD models to real-world scans.

Abstract

We present Scan2CAD, a novel data-driven method that learns to align clean 3D CAD models from a shape database to the noisy and incomplete geometry of a commodity RGB-D scan. For a 3D reconstruction of an indoor scene, our method takes as input a set of CAD models, and predicts a 9DoF pose that aligns each model to the underlying scan geometry. To tackle this problem, we create a new scan-to-CAD alignment dataset based on 1506 ScanNet scans with 97607 annotated keypoint pairs between 14225 CAD models from ShapeNet and their counterpart objects in the scans. Our method selects a set of representative keypoints in a 3D scan for which we find correspondences to the CAD geometry. To this end, we design a novel 3D CNN architecture that learns a joint embedding between real and synthetic objects, and from this predicts a correspondence heatmap. Based on these correspondence heatmaps, we formulate a variational energy minimization that aligns a given set of CAD models to the reconstruction. We evaluate our approach on our newly introduced Scan2CAD benchmark where we outperform both handcrafted feature descriptor as well as state-of-the-art CNN based methods by 21.39%.