GRACE predicts dense human-scene contact on arbitrary 3D human point clouds from a single RGB image using a point cloud encoder-decoder with cross-modal attention, avoiding dependence on SMPL vertex ordering.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images
GRACE predicts dense human-scene contact on arbitrary 3D human point clouds from a single RGB image using a point cloud encoder-decoder with cross-modal attention, avoiding dependence on SMPL vertex ordering.