LINR Bridge: Vector Graphic Animation via Neural Implicits and Video Diffusion Priors

2025-09-09

AI Summary

This work addresses the challenge of simultaneously achieving infinite scalability, precise geometric/color constraints, and high-fidelity motion in vector graphic animation generation. We propose a novel method integrating implicit neural representations with text-to-video diffusion models. Our approach introduces a hierarchical implicit neural representation that explicitly encodes paths, shapes, and deformations—thereby bridging the semantic gap between the vector domain and diffusion-based video synthesis. To ensure temporal coherence, we incorporate Video Score Distillation Sampling (VSDS), and employ differentiable deformation mapping to preserve structural integrity during motion synthesis. Experiments demonstrate significant improvements over prior methods in animation naturalness, geometric and chromatic fidelity, and editing flexibility. To our knowledge, this is the first framework enabling end-to-end, controllable, high-fidelity vector graphic animation generation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Vector graphics, known for their scalability and user-friendliness, provide a unique approach to visual content compared to traditional pixel-based images. Animation of these graphics, driven by the motion of their elements, offers enhanced comprehensibility and controllability but often requires substantial manual effort. To automate this process, we propose a novel method that integrates implicit neural representations with text-to-video diffusion models for vector graphic animation. Our approach employs layered implicit neural representations to reconstruct vector graphics, preserving their inherent properties such as infinite resolution and precise color and shape constraints, which effectively bridges the large domain gap between vector graphics and diffusion models. The neural representations are then optimized using video score distillation sampling, which leverages motion priors from pretrained text-to-video diffusion models. Finally, the vector graphics are warped to match the representations resulting in smooth animation. Experimental results validate the effectiveness of our method in generating vivid and natural vector graphic animations, demonstrating significant improvement over existing techniques that suffer from limitations in flexibility and animation quality.

Problem

• Automating vector graphic animation to reduce manual effort
• Bridging domain gap between vector graphics and diffusion models
• Generating smooth animations with improved flexibility and quality

Innovation

• Implicit neural representations reconstruct vector graphics
• Video score distillation leverages diffusion motion priors
• Warped vector graphics produce smooth animations