VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A single continuous 4D B-spline wire with variable width can represent complex 3D forms with enforced global topological coherence better than collections of independent curves.
citing papers explorer
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
Optimizing 4D Wires for Sparse 3D Abstraction
A single continuous 4D B-spline wire with variable width can represent complex 3D forms with enforced global topological coherence better than collections of independent curves.