A prior-guided residual flow matching framework with dynamic cross-interaction reports state-of-the-art results on 3D multi-person motion forecasting benchmarks.
InProceedings of the IEEE/CVF International Conference on Computer Vision, 10844–10853
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion Prediction
A prior-guided residual flow matching framework with dynamic cross-interaction reports state-of-the-art results on 3D multi-person motion forecasting benchmarks.