SVG360: Multi-View SVG Generation with Geometric and Color Consistency from a Single SVG
This work addresses the underexplored challenge of multi-view SVG generation for object-level assets, supporting applications like asset creation and semantic vector editing, but it is incremental as it builds on existing methods like SAM2.
The authors tackled the problem of generating multi-view consistent SVGs from a single SVG input, resulting in SVGs with strong geometric and color consistency, reduced redundant paths, and preserved fine details.
Scalable Vector Graphics (SVGs) are central to modern design workflows, offering scaling without distortion and precise editability. However, for single object SVGs, generating multi-view consistent SVGs from a single-view input remains underexplored. We present a three stage framework that produces multi-view SVGs with geometric and color consistency from a single SVG input. First, the rasterized input is lifted to a 3D representation and rendered under target camera poses, producing multi-view images of the object. Next, we extend the temporal memory mechanism of Segment Anything 2 (SAM2) to the spatial domain, constructing a spatial memory bank that establishes part level correspondences across neighboring views, yielding cleaner and more consistent vector paths and color assignments without retraining. Finally, during the raster to vector conversion, we perform path consolidation and structural optimization to reduce redundancy while preserving boundaries and semantics. The resulting SVGs exhibit strong geometric and color consistency across views, significantly reduce redundant paths, and retain fine structural details. This work bridges generative modeling and structured vector representation, providing a scalable route to single input, object level multi-view SVG generation and supporting applications such as asset creation and semantic vector editing.