轻量级点云模型仅用3.9万数据即超越更大数据量模型。
Pointy - A Lightweight Transformer for Point Cloud Foundation Models
- 采用轻量Transformer架构，无需跨模态监督
- 3.9万点云训练即超越20万+样本模型表现
- 适合追求高效与可复现性的点云研究者
点云基础模型近年来能力不断提升，常依赖语言或视觉的大量表示学习。本文提出一种轻量级基于Transformer的点云架构，不依赖跨模态监督，仅在3.9万点云上训练，却优于多个在超过20万样本上训练的更大模型。有趣的是，其性能接近使用超百万点云、图像和文本样本的模型，凸显精心设计的训练设置与架构的价值。为确保严谨评估，我们开展全面复现研究，统一训练流程，在多个点云架构间基准测试。该统一实验框架隔离了架构选择的影响，实现透明比较，突出我们设计及无分词器架构的优势。结果表明，简单骨干网络可媲美复杂或数据密集型策略。代码、预训练模型及训练协议已在GitHub公开：https://github.com/KonradSzafer/Pointy。
原文摘要 · Abstract (English)
Foundation models for point cloud data have recently grown in capability, often leveraging extensive representation learning from language or vision. In this work, we take a more controlled approach by introducing a lightweight transformer-based point cloud architecture. In contrast to the heavy reliance on cross-modal supervision, our model is trained only on 39k point clouds - yet it outperforms several larger foundation models trained on over 200k training samples. Interestingly, our method approaches state-of-the-art results from models that have seen over a million point clouds, images, and text samples, demonstrating the value of a carefully curated training setup and architecture. To ensure rigorous evaluation, we conduct a comprehensive replication study that standardizes the training regime and benchmarks across multiple point cloud architectures. This unified experimental framework isolates the impact of architectural choices, allowing for transparent comparisons and highlighting the benefits of our design and other tokenizer-free architectures. Our results show that simple backbones can deliver competitive results to more complex or data-rich strategies. The implementation, including code, pre-trained models, and training protocols, is available at https://github.com/KonradSzafer/Pointy.
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。