用多头结构提升点云重建效率，打破越深越好的固有认知
Less is More: Efficient Point Cloud Reconstruction via Multi-Head Decoders
- 设计多头解码器，从不同点子集独立重建形状
- 在ModelNet40和ShapeNetPart上各项指标均优于单头基线
- 证明多样性与架构设计比深度更重要
我们质疑了深度解码器架构必然带来更好性能的普遍假设。分析表明，超过一定深度后，解码器复杂度增加会导致过拟合、泛化能力下降。为此，我们提出一种新型多头解码器，利用点云内在冗余性，通过多个独立头分别处理不同点子集来重建完整形状，最终输出为各头预测结果的拼接，提升了输出多样性与保真度。在ModelNet40和ShapeNetPart上的大量实验显示，该方法在Chamfer Distance (CD)、Hausdorff Distance (HD)、Earth Mover's Distance (EMD)和F1-score等关键指标上持续优于标准单头基线。研究结果表明，输出多样性与架构设计对高效点云重建更为关键。
原文摘要 · Abstract (English)
We challenge the common assumption that deeper decoder architectures always yield better performance in point cloud reconstruction. Our analysis reveals that, beyond a certain depth, increasing decoder complexity leads to overfitting and degraded generalization. Additionally, we propose a novel multi-head decoder architecture that exploits the inherent redundancy in point clouds by reconstructing complete shapes from multiple independent heads, each operating on a distinct subset of points. The final output is obtained by concatenating the predictions from all heads, enhancing both diversity and fidelity. Extensive experiments on ModelNet40 and ShapeNetPart demonstrate that our approach achieves consistent improvements across key metrics--including Chamfer Distance (CD), Hausdorff Distance (HD), Earth Mover's Distance (EMD), and F1-score--outperforming standard single-head baselines. Our findings highlight that output diversity and architectural design can be more critical than depth alone for effective and efficient point cloud reconstruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。