Efficient RWKV-based Representation Learning for 3D Point Clouds

• URL: http://arxiv.org/abs/2606.10395v1
• Date: Tue, 09 Jun 2026 04:16:39 GMT
• Title: Efficient RWKV-based Representation Learning for 3D Point Clouds
• Abstract summary: The textbfP-RWKV block bridges the gap between sequence modeling and irregular 3D geometry.<n>The P-RWKV block and its key sub-modules achieve competitive performance across various tasks with lower computational cost and inference latency.
• Score: 53.911842457391636
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling global dependencies. However, when directly applied to point clouds, RWKV, originally developed for sequential text, struggles to capture local geometric structures and model spatial dependencies effectively. To address this, we propose the \textbf{P-RWKV} block, which bridges the gap between sequence modeling and irregular 3D geometry while preserving the efficiency advantages of RWKV. It consists of a Local Perception Expansion (LPE) component to expand contextual perception along the spatio-temporal sequence and a Spatial Context Enhancement (SCE) component to strengthen spatial awareness. To validate the effectiveness of P-RWKV for point cloud understanding, we construct PointER, a single-modality self-supervised representation learning framework whose encoder is composed of stacked P-RWKV blocks. Furthermore, we extend P-RWKV to a cross-modality setting and integrate the proposed core sub-modules into multiple architectures, demonstrating strong plug-and-play flexibility and architectural generality. Extensive experiments show that the P-RWKV block and its key sub-modules achieve competitive performance across various tasks with lower computational cost and inference latency. Code will be released upon acceptance.

Related papers

• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV [15.840121055564405]
  KAN-We-Flow is a flow-matching policy that builds a lightweight backbone for 3D manipulation.<n>Our design reduces parameters by 86.8%, maintains fast runtime, and achieves state-of-the-art success rates on Adroit, Meta-World, and DexArt benchmarks.
  arXiv  Detail & Related papers  (2026-02-01T09:27:56Z)
• Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes [60.92139345612904]
  We present Light-SQ, a novel superquadric-based optimization framework.<n>We propose a block-regrow-fill strategy guided by structure-aware volumetric decomposition.<n>Experiments demonstrate that Light-SQ enables efficient, high-fidelity, and editable shape abstraction with superquadrics.
  arXiv  Detail & Related papers  (2025-09-29T16:18:32Z)
• PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification [122.95228430332816]
  Point Domain Generalization (DG) has been recently explored to enhance the generalizability of Point Cloud Classification (PCC) models toward unseen domains.<n>We present the first work that studies the generalizability of RWKV models in DG PCC.<n>We propose PointDGRWKV, the first RWKV-based framework tailored for DG PCC.
  arXiv  Detail & Related papers  (2025-08-28T14:28:33Z)
• U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV [13.528706926224114]
  We propose U-RWKV, a novel framework for efficient long-range modeling at O(N) computational cost.<n>The framework introduces two key innovations: the Direction-Adaptive RWKV Module and the Stage-Adaptive Squeeze-and-Excitation Module.<n>Experiments demonstrate that U-RWKV achieves state-of-the-art segmentation performance with high computational efficiency.
  arXiv  Detail & Related papers  (2025-07-15T15:40:17Z)
• RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image Segmentation [70.79072961974141]
  We propose RWKV-UNet, a novel model that integrates the RWKV structure into the U-Net architecture.<n>This integration enhances the model's ability to capture long-range dependencies and to improve contextual understanding.<n> Experiments on 11 benchmark datasets show that the RWKV-UNet achieves state-of-the-art performance on various types of medical image segmentation tasks.
  arXiv  Detail & Related papers  (2025-01-14T22:03:00Z)
• PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning [56.14518823931901]
  We present PointRWKV, a model of linear complexity derived from the RWKV model in the NLP field. We first propose to explore the global processing capabilities within PointRWKV blocks using modified multi-headed matrix-valued states. To extract local geometric features simultaneously, we design a parallel branch to encode the point cloud efficiently in a fixed radius near-neighbors graph with a graph stabilizer.
  arXiv  Detail & Related papers  (2024-05-24T05:02:51Z)
• Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching [35.80653765524654]
  3D dynamic point cloud (DPC) compression relies on mining its temporal context. This paper proposes a learning-based DPC compression framework via hierarchical block-matching-based inter-prediction module.
  arXiv  Detail & Related papers  (2023-05-09T11:44:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.