用紧凑隐空间高效表示高精度3D形状的神经符号距离函数
Learning Compact Latent Space for Representing Neural Signed Distance Functions with High-fidelity Geometry Details
- 结合泛化与过拟合学习策略，提升隐空间表达能力
- 在多个基准上实现更高保真度几何还原与更小隐码尺寸
- 适合需要高效存储和高精度重建的3D生成任务
神经符号距离函数（SDF）是用神经网络表示3D形状或场景的重要隐式表征方式，通过查询特定坐标处的带符号距离来恢复3D表面。尽管单个形状或场景的SDF表现良好，但在分析多个带有高保真几何细节的SDF时，受限于其隐空间编码信息有限且易丢失几何细节，面临挑战。为此，本文提出一种在公共空间中表示多个SDF的方法，旨在以更紧凑的隐码恢复更多高保真几何细节。核心思想是充分利用基于泛化和基于过拟合的学习策略，分别有效保留细节并压缩表示。在此框架下，我们还设计了一种新型采样策略，用于训练查询采样，提升训练效率，并消除其他SDF带来的伪影。我们在多个主流基准上进行了数值与可视化评估，验证了设计的有效性，结果表明该方法在表征能力与紧凑性方面优于最新技术。
原文摘要 · Abstract (English)
Neural signed distance functions (SDFs) have been a vital representation to represent 3D shapes or scenes with neural networks. An SDF is an implicit function that can query signed distances at specific coordinates for recovering a 3D surface. Although implicit functions work well on a single shape or scene, they pose obstacles when analyzing multiple SDFs with high-fidelity geometry details, due to the limited information encoded in the latent space for SDFs and the loss of geometry details. To overcome these obstacles, we introduce a method to represent multiple SDFs in a common space, aiming to recover more high-fidelity geometry details with more compact latent representations. Our key idea is to take full advantage of the benefits of generalization-based and overfitting-based learning strategies, which manage to preserve high-fidelity geometry details with compact latent codes. Based on this framework, we also introduce a novel sampling strategy to sample training queries. The sampling can improve the training efficiency and eliminate artifacts caused by the influence of other SDFs. We report numerical and visual evaluations on widely used benchmarks to validate our designs and show advantages over the latest methods in terms of the representative ability and compactness.
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。