Paper Review: Wakey-Wakey: Animate Text by Mimicking Characters in a GIF

DOI

Problem

  • Kinetic Typography has limitations (challenging and time-consuming)
  • previous way (alleviate the authoring burden) -> but limited customizability)

Solution

  • Use GIF trajectories of several key points
  • User can customize and refine -> more desirable output

Design Space

  • Both direct generation and fine-grain refinement
    • Direct generation:
      • Generalize to various user requirements
    • Fine-grain refinement:
      • Address uncertainty problem
  • Empower creators with interpretable algorithmic parameters
    • Providing explanations for the generation process
      • Can provide feedback and make adjustments at every step of generation process
  • Human Experience + Supervision = Higher quality and more consistent generations in the line with users’ expectation

Authoring Experience

  • Different View:
    • Input View: Mandatory

      • Users first input
    • Correction View: Optional

      • Drag the displayed the key points from the motion trajectory extraction module to a suitable location
    • Refinement View: Optional

      • Configure the parameters a and e
      • Select whether the kinetic typography is generated by aligning to key points
Hyungjun Doh
Hyungjun Doh
Master’s Student

My research interests are Human-AI interaction and its practical applications, with a specific focus on Extended Reality, Task Guidance Systems, and AI-infused interfaces.