Publications
EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation
A flow-matching framework with gradient-guided inference that generates physically plausible 6DoF object trajectories from egocentric videos, reducing collision rates by up to 79%.
GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes
A multimodal transformer framework that generates realistic and goal-directed 6-DOF object trajectories by jointly leveraging 3D bounding box geometry, point cloud context, semantic object categories, and target end poses.
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
A latent diffusion model with nonisotropic Gaussian noise aligned to the human skeleton's kinematic structure for realistic 3D motion prediction.
GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fields
Joint appearance and geometry stylization in dynamic radiance fields, transferring both color and structural details from style images.
ZDySS: Zero-Shot Dynamic Scene Stylization using Gaussian Splatting
A zero-shot stylization framework for dynamic scenes using Gaussian Splatting that generalizes to unseen style images at inference.
DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting
A novel symmetric and differentiable Chamfer distance loss for neural implicit surface fitting that eliminates spurious surfaces without additional regularization.
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations
Curvature-guided sampling and uncertainty-augmented representations for improved neural implicit surface reconstruction.
Gaussian Splatting in Style
We are the first to employ Gaussian Splatting to solve the task of scene stylization, extending the work of neural style transfer to three spatial dimensions.
ResolvNet: A Graph Convolutional Network with multi-scale Consistency
A spectral graph convolutional architecture with multi-scale consistency for weighted graphs.