DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion

TL;DR

This paper introduces DAPoinTr, a novel domain adaptive point transformer framework for point cloud completion, which effectively reduces domain gaps through feature alignment and ensemble voting, outperforming existing methods.

Contribution

The paper proposes a pioneering domain adaptive framework for point cloud completion, introducing novel feature alignment modules and ensemble voting strategies to enhance transferability.

Findings

DAPoinTr outperforms state-of-the-art methods on multiple benchmarks.

The proposed modules effectively reduce domain gaps in point cloud data.

Visualization results demonstrate improved completion quality across domains.

Abstract

Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, we delve into this topic and empirically discover that direct feature alignment on point Transformer's CNN backbone only brings limited improvements since it cannot guarantee sequence-wise domain-invariant features in the Transformer. To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three key components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC). In particular, DQFA is presented to narrow the global domain gaps from the sequence via the presented domain proxy and domain query at the Transformer encoder and decoder, respectively. PTFA is proposed to close the local domain shifts by aligning the tokens, \emph{i.e.,} point proxy and dynamic query, at the Transformer encoder and decoder, respectively. VPC is designed to consider different Transformer decoders as multiple of experts (MoE) for ensembled prediction voting and pseudo-label generation. Extensive experiments with visualization on several domain adaptation benchmarks demonstrate the effectiveness and superiority of our DAPoinTr compared with state-of-the-art methods. Code will be publicly available at: https://github.com/Yinghui-Li-New/DAPoinTr