· 2019
On the Continuity of Rotation Representations in Neural Networks
- 1,146citations
- 2019year
Short summary
Neural networks can learn 3D rotations more effectively using continuous representations in 5D or 6D spaces, as common representations like quaternions and Euler angles are discontinuous.
AI-generated from the title and abstract; the full text is not read.
TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app
The rest is in the Pofolia app
Takeaways, key points and questions to the paper; new summaries every day for your field. Free.
Sign in on the web to openField: Computational Mechanics
Computational MechanicsEngineering