CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
Smpl: A skinned multi- person linear model
3 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
The contact matrix approach in a diffusion model, paired with specialized VQ-VAE, enables more precise and realistic generation of interactive duet dance motions compared to prior methods.
A new physics-aware motion synthesis method that models full human-object, human-scene, and internal body forces with soft balance constraints and a continuous distance-based force model for arbitrary surfaces.
citing papers explorer
-
CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
-
Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling
The contact matrix approach in a diffusion model, paired with specialized VQ-VAE, enables more precise and realistic generation of interactive duet dance motions compared to prior methods.
-
InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene
A new physics-aware motion synthesis method that models full human-object, human-scene, and internal body forces with soft balance constraints and a continuous distance-based force model for arbitrary surfaces.