cs.CVNov 7, 2026

DAPointRWKV: Domain Adaptive Vision RWKV for Point Cloud Completion

Authors: Yinghui Li, Qianyu Zhou, Hao Yang, Richard Dazeley, Ye Zhu, Xuequan Lu

Organizations: Deakin University, Waurn Ponds, Victoria, Australia · The University of Tokyo, Tokyo, Japan · Shanghai Jiao Tong University, Shanghai, China · Deakin University, Burwood, Victoria, Australia · 

Abstract

Domain adaptive point cloud completion (DA PCC) aims to bridge the geometric discrepancy between labeled source domains and unlabeled target domains for accurate 3D shape completion. Existing methods based on CNNs, Transformers, and Mamba-like sequence models still face challenges from limited receptive fields, high computational complexity, insufficient geometric bias, and serialization sensitivity. Recently, Receptance Weighted Key Value (RWKV) provides a linear-complexity alternative for long-range sequence modeling. However, adapting RWKV to DA PCC remains challenging due to the lack of explicit geometric priors, the mismatch between recurrent modeling and coarse-to-fine generation, and unstable target-domain adaptation. To address these challenges, we propose DAPointRWKV, a novel RWKV-based framework for DA PCC. DAPointRWKV consists of three components: Geometry-Aware RWKV (GA-RWKV) Backbone, RWKV-Oriented Progressive Decoder (RWKV-PD), and Dual Structural Regularization (DSR). Specifically, GA-RWKV introduces geometry-aware recurrent representation learning, RWKV-PD bridges RWKV token representations with coarse-to-fine reconstruction through local token-guided refinement, and DSR stabilizes target-domain transfer through visible-structure anchoring and complete-shape hypothesis stabilization. Extensive experiments on synthetic and real-world benchmarks demonstrate that DAPointRWKV consistently outperforms state-of-the-art methods.

Figures & tables

Explore similar work

CardsList
  1. Efficient RWKV-based Representation Learning for 3D Point Clouds

    Jun 9, 2026Yun Liu, Xuefeng Yan, Liangliang Nan +5Self-Supervised Point Cloud LearningPoint Cloud Learning

  2. PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecture

    Mar 1, 2026Jie Li, Shengwei Tian, Long Yu +1Point Cloud CompletionParallel Decoding

  3. I2PRef: Image-Driven Point Completion with Iterative Refinement

    May 26, 2026Azhar Hussian, Marina Ritthaler, André Kaup +1Point Cloud Completion3D Reconstruction