Presentation

<
Articulate That Object Part (ATOP): 3D Part Articulation from Text and via Motion Personalization
SessionDynamic Scenes
DescriptionWe present a few-shot method for articulating static 3D objects using text-guided motion personalization. Leveraging diffusion models, we generate plausible part motions and adapt them to input objects via image prompting. Differentiable rendering with score distillation transfers multi-view motion into 3D, enabling optimization of articulation parameters under piecewise rigidity assumptions.
Authors
Aditya Vora
Simon Fraser University
Sauradip Nag
Simon Fraser University
Kai Wang
Simon Fraser University
Hao (Richard) Zhang
Simon Fraser University
Presenter
Aditya Vora
Simon Fraser University
Event Type
Technical Paper
TimeTuesday, 21 July 202611:35am - 11:45am PDT
LocationRoom 408 B
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 202610:45am - 12:15pm PDTRoom 408 B
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationDynamic Scenes - Interactive Discussion
Similar Presentations
Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects
Emerging Technologies Demo - Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects
PEGAsus: 3D Personalization of Geometry and Appearance