3 papers
cs.CV2026
VISTA: Video-Injected Stylized Text-to-Animation
Monseej Purkayastha, Anindita Ghosh, Philipp Slusallek
We present VISTA, a two-stage framework for generating stylized 3D human motion by fusing structural content from text prompts with expressive style from reference videos, without…
cs.CV2026
SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens
Anindita Ghosh, Vladislav Golyanik, Taku Komura +3
Synthesizing text-driven 3D human motion within realistic scenes requires learning both semantic intent ("walk to the couch") and physical feasibility (e.g., avoiding collisions).…
cs.GR2025
DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling
Anindita Ghosh, Bing Zhou, Rishabh Dabral +5
We present DuetGen, a novel framework for generating interactive two-person dances from music. The key challenge of this task lies in the inherent complexities of two-person dance…