RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Wenzhe, Chen, Xiaojun, Chen, Wentang, Wang, Hongyu, Liu, Ying, Li, Ruihui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908650134568960
author He, Wenzhe
Chen, Xiaojun
Chen, Wentang
Wang, Hongyu
Liu, Ying
Li, Ruihui
author_facet He, Wenzhe
Chen, Xiaojun
Chen, Wentang
Wang, Hongyu
Liu, Ying
Li, Ruihui
contents Semantic Scene Completion (SSC) aims to generate a complete semantic scene from an incomplete input. Existing approaches often employ dense network architectures with a high parameter count, leading to increased model complexity and resource demands. To address these limitations, we propose RWKV-PCSSC, a lightweight point cloud semantic scene completion network inspired by the Receptance Weighted Key Value (RWKV) mechanism. Specifically, we introduce a RWKV Seed Generator (RWKV-SG) module that can aggregate features from a partial point cloud to produce a coarse point cloud with coarse features. Subsequently, the point-wise feature of the point cloud is progressively restored through multiple stages of the RWKV Point Deconvolution (RWKV-PD) modules. By leveraging a compact and efficient design, our method achieves a lightweight model representation. Experimental results demonstrate that RWKV-PCSSC reduces the parameter count by 4.18$\times$ and improves memory efficiency by 1.37$\times$ compared to state-of-the-art methods PointSSC. Furthermore, our network achieves state-of-the-art performance on established indoor (SSC-PC, NYUCAD-PC) and outdoor (PointSSC) scene dataset, as well as on our proposed datasets (NYUCAD-PC-V2, 3D-FRONT-PC).
format Preprint
id arxiv_https___arxiv_org_abs_2511_09878
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion
He, Wenzhe
Chen, Xiaojun
Chen, Wentang
Wang, Hongyu
Liu, Ying
Li, Ruihui
Computer Vision and Pattern Recognition
Semantic Scene Completion (SSC) aims to generate a complete semantic scene from an incomplete input. Existing approaches often employ dense network architectures with a high parameter count, leading to increased model complexity and resource demands. To address these limitations, we propose RWKV-PCSSC, a lightweight point cloud semantic scene completion network inspired by the Receptance Weighted Key Value (RWKV) mechanism. Specifically, we introduce a RWKV Seed Generator (RWKV-SG) module that can aggregate features from a partial point cloud to produce a coarse point cloud with coarse features. Subsequently, the point-wise feature of the point cloud is progressively restored through multiple stages of the RWKV Point Deconvolution (RWKV-PD) modules. By leveraging a compact and efficient design, our method achieves a lightweight model representation. Experimental results demonstrate that RWKV-PCSSC reduces the parameter count by 4.18$\times$ and improves memory efficiency by 1.37$\times$ compared to state-of-the-art methods PointSSC. Furthermore, our network achieves state-of-the-art performance on established indoor (SSC-PC, NYUCAD-PC) and outdoor (PointSSC) scene dataset, as well as on our proposed datasets (NYUCAD-PC-V2, 3D-FRONT-PC).
title RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.09878