DeSeG decouples semantic intent from geometric constraints in human-scene interaction synthesis using a residual CVAE planner and a physics-regularized diffusion executor, reducing scene penetration by 47% and improving semantic alignment by 29% over SOTA baselines on the Lingo dataset.
Hierarchical generation of human-object interactions with diffusion probabilistic models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DeSeG: Decoupling Semantic Intent and Geometric Constraints for Physically Plausible Human-Scene Interaction
DeSeG decouples semantic intent from geometric constraints in human-scene interaction synthesis using a residual CVAE planner and a physics-regularized diffusion executor, reducing scene penetration by 47% and improving semantic alignment by 29% over SOTA baselines on the Lingo dataset.