ESCAPE: Equivariant Shape Completion via Anchor Point Encoding

TL;DR

ESCAPE introduces a rotation-equivariant shape completion framework using anchor point encoding and transformers, enabling accurate 3D shape reconstruction under arbitrary rotations without pose estimation.

Contribution

The paper proposes a novel anchor point encoding strategy combined with transformers to achieve rotation-equivariant shape completion, improving robustness to orientation variations.

Findings

Achieves high-quality shape reconstructions under arbitrary rotations.

Outperforms existing methods in robustness and accuracy.

Operates effectively without pose estimation modules.

Abstract

Shape completion, a crucial task in 3D computer vision, involves predicting and filling the missing regions of scanned or partially observed objects. Current methods expect known pose or canonical coordinates and do not perform well under varying rotations, limiting their real-world applicability. We introduce ESCAPE (Equivariant Shape Completion via Anchor Point Encoding), a novel framework designed to achieve rotation-equivariant shape completion. Our approach employs a distinctive encoding strategy by selecting anchor points from a shape and representing all points as a distance to all anchor points. This enables the model to capture a consistent, rotation-equivariant understanding of the object's geometry. ESCAPE leverages a transformer architecture to encode and decode the distance transformations, ensuring that generated shape completions remain accurate and equivariant under rotational transformations. Subsequently, we perform optimization to calculate the predicted shapes from the encodings. Experimental evaluations demonstrate that ESCAPE achieves robust, high-quality reconstructions across arbitrary rotations and translations, showcasing its effectiveness in real-world applications without additional pose estimation modules.