NeuralSVG encodes a text-prompted vector graphic as the weights of a small MLP, using nested dropout so the first learned shapes are semantically meaningful and editable.
In Proceedings of the AAAI Conference on Artificial Intelligence , Vol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NeuralSVG: An Implicit Representation for Text-to-Vector Generation
NeuralSVG encodes a text-prompted vector graphic as the weights of a small MLP, using nested dropout so the first learned shapes are semantically meaningful and editable.