HOGS renders physically plausible human-object interactions from sparse views by optimizing dynamic 3D Gaussians with contact/separation losses guided by pre-trained pose refiner and contact predictor modules, claiming SOTA quality and efficiency.
Keep it smpl: Automatic estimation of 3d human pose and shape from a single image
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A framework disentangles local joint motion from global movement, trains a 2D local generator on text-2D pairs, then fine-tunes on 3D data to output view-consistent 3D motions.
citing papers explorer
-
Physically Plausible Human-Object Rendering from Sparse Views via 3D Gaussian Splatting
HOGS renders physically plausible human-object interactions from sparse views by optimizing dynamic 3D Gaussians with contact/separation losses guided by pre-trained pose refiner and contact predictor modules, claiming SOTA quality and efficiency.
-
Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
A framework disentangles local joint motion from global movement, trains a 2D local generator on text-2D pairs, then fine-tunes on 3D data to output view-consistent 3D motions.