A framework called Policy-as-Data generates task-oriented synthetic HOI data via RL policies in physics simulators, retargets it, and trains diffusion models that generalize to unseen objects and long horizons.
In: SIGGRAPH Asia 2024 Con- ference Papers
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
SplatShot is a training-free method that inserts per-step 3DGS refitting and photometric feedback into diffusion denoising to enforce multi-view consistency for single-photo 3D face avatars.
COSY uses independent per-component 3DGS generators plus context tokens to achieve disentangled semantic editing of human heads without masks or classifiers.
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
OctaOctree is a hybrid spatial-angular data structure for neural radiosity that enables real-time, high-quality rendering of glossy global illumination effects.
A neural formulation combining light tracing, normalizing flows, and distilled MLPs to estimate and render appearance of complex luminaires.
citing papers explorer
-
BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.