提出首个满足SIM(3)等变性的3D形状补全模型，提升真实场景泛化能力。
Learning Generalizable Shape Completion with SIM(3) Equivariance
- 设计模块化网络，逐步归一化特征、推理相似不变几何、恢复原始坐标系
- 在去偏评估下，KITTI上最小匹配距离降低17%，OmniObject3D上Chamfer距离降低14%
- 即使在更严格条件下仍优于其他模型在有偏差设置下的表现，适合跨域真实数据应用
3D形状补全方法通常假设扫描数据已对齐至标准坐标系，这会泄露姿态和尺度信息，导致网络记忆绝对位置而非推断内在几何。当真实数据中无此对齐时，性能急剧下降。本文主张鲁棒泛化需架构具备相似性群SIM(3)的等变性，使模型对姿态和尺度保持无关性。据此，我们提出首个SIM(3)-等变的形状补全网络，其模块化层依次完成特征归一化、相似性不变几何推理、原始框架恢复。在去除隐含线索的去偏评估协议下，本模型在PCN基准上超越等变与增强基线。在真实驾驶与室内扫描数据上创下跨域新纪录：KITTI上最小匹配距离降低17%，OmniObject3D上Chamfer距离ℓ1降低14%。令人意外的是，在更严格的协议下，本模型仍优于其他模型在有偏差设置下的表现。结果确立了完整SIM(3)等变性作为真正泛化形状补全的有效路径。
原文摘要 · Abstract (English)
3D shape completion methods typically assume scans are pre-aligned to a canonical frame. This leaks pose and scale cues that networks may exploit to memorize absolute positions rather than inferring intrinsic geometry. When such alignment is absent in real data, performance collapses. We argue that robust generalization demands architectural equivariance to the similarity group, SIM(3), so the model remains agnostic to pose and scale. Following this principle, we introduce the first SIM(3)-equivariant shape completion network, whose modular layers successively canonicalize features, reason over similarity-invariant geometry, and restore the original frame. Under a de-biased evaluation protocol that removes the hidden cues, our model outperforms both equivariant and augmentation baselines on the PCN benchmark. It also sets new cross-domain records on real driving and indoor scans, lowering minimal matching distance on KITTI by 17% and Chamfer distance $\ell1$ on OmniObject3D by 14%. Perhaps surprisingly, ours under the stricter protocol still outperforms competitors under their biased settings. These results establish full SIM(3) equivariance as an effective route to truly generalizable shape completion. Project page: https://sime-completion.github.io.
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。