4 papers
AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
Juncheng Hu, Ziteng Xue, Guotao Liang +5
We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Exis…
Beyond the Visible: Disocclusion-Aware Editing via Proxy Dynamic Graphs
Anran Qi, Changjian Li, Adrien Bousseau +1
We address image-to-video generation with explicit user control over the final frame's disoccluded regions. Current image-to-video pipelines produce plausible motion but struggle t…
GarmentImage: Raster Encoding of Garment Sewing Patterns with Diverse Topologies
Yuki Tatsukawa, Anran Qi, I-Chao Shen +1
Garment sewing patterns are the design language behind clothing, yet their current vector-based digital representations weren't built with machine learning in mind. Vector-based re…
FontCraft: Multimodal Font Design Using Interactive Bayesian Optimization
Yuki Tatsukawa, I-Chao Shen, Mustafa Doga Dogan +4
Creating new fonts requires a lot of human effort and professional typographic knowledge. Despite the rapid advancements of automatic font generation models, existing methods requi…