The single-view image guided point cloud completion (SVIPC) task aims to reconstruct a complete point cloud from a partial input with the help of a single-view image. While previous works have demonstrated the effectiveness of this multimodal approach, the fundamental necessity of image guidance remains largely unexamined. To explore this, we propose a strong baseline approach for SVIPC based on an attention-based multi-branch encoder-decoder network that only takes partial point clouds as input, view-free. Our hierarchical self-fusion mechanism, driven by cross-attention and self-attention layers, effectively integrates information across multiple streams, enriching feature representations and strengthening the networks ability to capture geometric structures. Extensive experiments and ablation studies on the ShapeNet-ViPC dataset demonstrate that our view-free framework performs superiorly to state-of-the-art SVIPC methods. We hope our findings provide new insights into the development of multimodal learning in SVIPC. Our demo code will be available at https://github.com/Zhang-VISLab.
@article{arxiv.2506.15747,
title = {A Strong View-Free Baseline Approach for Single-View Image Guided Point Cloud Completion},
author = {Fangzhou Lin and Zilin Dai and Rigved Sanku and Songlin Hou and Kazunori D Yamada and Haichong K. Zhang and Ziming Zhang},
journal= {arXiv preprint arXiv:2506.15747},
year = {2025}
}