SO(3)-Equivariant Learning on CAD Boundary Representations
cs.CV, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/UGent-CVAMO/so3brep
Terminology
Sources
- CAD-feature enhanced machine learning for manufacturing effort estimation on sheet metal bending parts
- NeuroNURBS: Learning Efficient Surface Representations for 3D Solids
- e3nn: Euclidean Neural Networks
- Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs