6 papers
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-…
SonoWorld: From One Image to a 3D Audio-Visual Scene
Derong Jin, Xiyi Chen, Ming C. Lin +1
Tremendous progress in visual scene generation now turns a single image into an explorable 3D world, yet immersion remains incomplete without sound. We introduce Image2AVScene, the…
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…
HART: Human Aligned Reconstruction Transformer
Xiyi Chen, Shaofei Wang, Marko Mihajlovic +3
We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh…