用SDF隐空间变压器完成3D形状补全，效果优于现有方法
POC-SLT: Partial Object Completion with SDF Latent Transformers
- 将SDF分解为小块隐码序列，用Transformer在隐空间补全
- 在ShapeNet和ABC数据集上，补全精度显著优于主流方法
- 适合做3D重建、几何生成的开发者和研究者参考
3D几何形状补全依赖于表示学习与对几何数据的深入理解。若缺乏对三维数据本质的深刻洞察，该任务难以实现。本文针对部分观测下的3D形状补全问题，提出一种在符号距离场（SDF）隐空间中运行的Transformer模型。不同于单一体积表示，该方法将物体的SDF划分为多个高分辨率子块，形成隐码序列。通过在数百万个3D块上训练的变分自编码器（VAE）学习平滑的隐空间编码，并采用高效的掩码自编码器变压器，在隐空间中将部分序列补全为完整形状。在ShapeNet和ABC数据集上的大量实验表明，仅提供部分对象的情况下，所提出的POC-SLT架构在定性和定量上均优于多个基准的最先进方法，显著提升了3D形状补全性能。
原文摘要 · Abstract (English)
3D geometric shape completion hinges on representation learning and a deep understanding of geometric data. Without profound insights into the three-dimensional nature of the data, this task remains unattainable. Our work addresses this challenge of 3D shape completion given partial observations by proposing a transformer operating on the latent space representing Signed Distance Fields (SDFs). Instead of a monolithic volume, the SDF of an object is partitioned into smaller high-resolution patches leading to a sequence of latent codes. The approach relies on a smooth latent space encoding learned via a variational autoencoder (VAE), trained on millions of 3D patches. We employ an efficient masked autoencoder transformer to complete partial sequences into comprehensive shapes in latent space. Our approach is extensively evaluated on partial observations from ShapeNet and the ABC dataset where only fractions of the objects are given. The proposed POC-SLT architecture compares favorably with several baseline state-of-the-art methods, demonstrating a significant improvement in 3D shape completion, both qualitatively and quantitatively.
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。