From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
Geometric analysis fundamentally distinguishes between \textit{extrinsic} and \textit{intrinsic} perspectives. The dominant paradigm in current 3D representation learning relies on either extrinsic spatial structures or high-level semantics, struggling to capture the essence of shape identity and underlying manifold topology. To bridge this gap, we introduce a novel 3D representation learning paradigm, namely \textbf{PRISM}, for \textbf{P}re-training, which learns isometric embeddings by \textbf{R}ecovering the \textbf{I}ntrinsic \textbf{S}urface geodesic \textbf{M}etric. PRISM incorporates a topology-enforcing objective that explicitly constrains the structure of latent space, alongside ...
| Authors | Yuming Zhao, Junhui Hou, Qijian Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 1 June 2026 |
| Last updated at source | 1 June 2026 |
Connected in the knowledge graph
- AidenZhaoy/PRISMModel · cited by
Models and datasets referencing this paper
- AidenZhaoy/PRISMModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.