Showing 2025Show all
3 papers · 1 filter
cs.CV2025
Text-Conditioned Background Generation for Editable Multi-Layer Documents
Taewon Kang, Joseph K J, Chris Tensmeyer +4
We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain readable, we employ a latent maskin…
cs.CV2025
Character-Centered Dialogue Generation from Scene-Level Prompts
Taewon Kang, Ming C. Lin
Recent advances in scene-based video generation enable coherent visual narratives from structured prompts, yet a key aspect of storytelling -- character-driven dialogue and speech…
cs.CV2025
Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling
Taewon Kang, Divya Kothandaraman, Ming C. Lin
Generating coherent long-form video sequences from discrete text prompts remains challenging due to difficulties in maintaining temporal coherence, semantic consistency, and scene-…