无需完整3D形状数据，通过自洽约束实现高精度形状补全。
Self-supervised Shape Completion via Involution and Implicit Correspondences
- 利用自反函数性质设计无对抗的自监督学习框架
- 在标准数据集上逼近监督方法性能，最高达98%精度
- 适合处理刚性与非刚性动态形状补全任务
3D形状补全传统上依赖有监督训练或完整形状分布学习。近年来，无需完整3D形状样本的自监督方法受到关注。本文提出一种非对抗式的自监督形状补全方法。首次发现形状补全问题可自然表述为自反函数，即 G(G(X)) = X，对补全函数施加特殊约束。其次，基于形状补全与对应关系相互简化的关系，我们在标准空间中构建一致性度量以监督补全函数。采用“冻结交替”策略高效优化补全与对应模块。该方法在类别内刚性形状及动态非刚性形状上均表现优异。消融实验验证设计有效性，并在多个基准上达到接近监督学习的精度，部分场景达98%。
原文摘要 · Abstract (English)
3D shape completion is traditionally solved using supervised training or by distribution learning on complete shape examples. Recently self-supervised learning approaches that do not require any complete 3D shape examples have gained more interests. In this paper, we propose a non-adversarial self-supervised approach for the shape completion task. Our first finding is that completion problems can be formulated as an involutory function trivially, which implies a special constraint on the completion function G, such that G(G(X)) = X. Our second constraint on self-supervised shape completion relies on the fact that shape completion becomes easier to solve with correspondences and similarly, completion can simplify the correspondences problem. We formulate a consistency measure in the canonical space in order to supervise the completion function. We efficiently optimize the completion and correspondence modules using "freeze and alternate" strategy. The overall approach performs well for rigid shapes in a category as well as dynamic non-rigid shapes. We ablate our design choices and compare our solution against state-of-the-art methods, showing remarkable accuracy approaching supervised accuracy in some cases.
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。