无需核函数的点云表面重建，通过序列化提升效率与精度。
NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization
- 将点云转为保持局部性的序列令牌，用Transformer建模特征。
- 多尺度聚合特征预测SDF，显著减少序列化带来的邻域误判。
- 在户外数据集上性能超越现有方法，速度更快且实现更简单。
我们提出一种新型大规模点云表面重建方法，通过将不规则点云高效转换为有符号距离场（SDF）。核心基于近期Transformer架构（如PointTransformerV3），将点云序列化为保持局部性的令牌序列，并通过聚合邻近令牌高效预测某点的SDF值，得益于序列化带来的快速近似邻域检索。我们在不同层级/尺度上对点云进行序列化，并非线性聚合特征以预测SDF。实验表明，多尺度聚合对克服序列化引入的近邻近似误差（如虚假负例）至关重要。该框架在准确率和效率上达到新基准：性能优于或接近最佳先前方法，延迟减半，且实现更简洁，尤其在稀疏网格方法表现不佳的室外数据集上优势明显。
原文摘要 · Abstract (English)
We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based architectures (i.e., PointTransformerV3), that serializes the point cloud into a locality-preserving sequence of tokens. We efficiently predict the SDF value at a point by aggregating nearby tokens, where fast approximate neighbors can be retrieved thanks to the serialization. We serialize the point cloud at different levels/scales, and non-linearly aggregate a feature to predict the SDF value. We show that aggregating across multiple scales is critical to overcome the approximations introduced by the serialization (i.e. false negatives in the neighborhood). Our frameworks sets the new state-of-the-art in terms of accuracy and efficiency (better or similar performance with half the latency of the best prior method, coupled with a simpler implementation), particularly on outdoor datasets where sparse-grid methods have shown limited performance.
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。