Taku Komura

20

Papers

99

Total Citations

Papers (20)

TLControl: Trajectory and Language Control for Human Motion Synthesis

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos

Surface Extraction from Neural Unsigned Distance Fields

TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer

PhaseMP: Robust 3D Pose Estimation via Phase-conditioned Human Motion Prior

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

Motion-2-to-3: Leveraging 2D Motion Data for 3D Motion Generations

FaceFormer: Speech-Driven 3D Facial Animation With Transformers

F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories

NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction