7 papers · 1 filter
TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models
Taewon Kang, Matthias Zwicker
Text-to-video diffusion models generate temporally coherent content from natural language, yet when a prompt describes an early scene that persists while a new event emerges on top…
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
Taewon Kang, Matthias Zwicker
Diffusion models generate realistic visual content, yet often fail to produce rare but plausible compositions. When prompted with combinations that are valid but underrepresented i…
NEGATE: Constrained Semantic Guidance for Linguistic Negation in Text-to-Video Diffusion
Taewon Kang, Ming C. Lin
Negation is a fundamental linguistic operator, yet it remains inadequately modeled in diffusion-based generative systems. In this work, we present a formal treatment of linguistic…
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…
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…
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-…
3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance
Taewon Kang, Divya Kothandaraman, Dinesh Manocha +1
Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they t…