Research
SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
arXiv:2610.21087v1 Announce Type: cross Abstract: We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking tr
arXiv:2610.21087v1 Announce Type: cross Abstract: We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking triggers a topological collapse, effectively forcing the model to hallucinate orientation without a reference frame. To resolve this, we introduce SIEVE (Scalar Invariant Extraction Via Equivariance), an SE(3)-equivariant self-supervised framework that compresses point cloud geometry into invariant scalar embeddings. At its core is the spherical projection mask, which preserves global pose while obfuscating local semantics, sidestepping the obstruction by construction. Experiments confirm that SIEVE circumvents the predicted collapse where constant and noise masks fail. On downstream point cloud tasks, the resulting embeddings improve over coordinate-based baselines and hand-crafted geometric descriptors, with the largest gains on generalization to unseen shape categories.
Related
- Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning
- Separation Power of Equivariant Neural Networks
- Neural Point-Forms
- Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning
Source: arXiv cs.AI | 2026-10-16