VGGT

The 'VGGT' dataset/benchmark is used to evaluate the visual-kinematic alignment of generated robot trajectories in diverse manipulation environments.

Papers using VGGT (5)

OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer2026V-Dreamer: Automating Robotic Simulation and Trajectory Synthesis via Video Generation Priors2026AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models2026SyncTwin: Fast Digital Twin Construction and Synchronization for Safe Robotic Manipulation2026Improving Robotic Manipulation with Efficient Geometry-Aware Vision Encoder2025