A new Virtual Multi-View Synthesis module improves pedestrian orientation estimation when integrated into the AVOD-FPN 3D detector, outperforming prior methods on KITTI Orientation, 3D, and Bird's Eye View benchmarks.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
unclear 1representative citing papers
Digital twin representations from vision foundation models enable LLM-based planning for robust peg transfer and gauze retrieval on the dVRK surgical platform with claimed generalizability.
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.
citing papers explorer
-
Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation
A new Virtual Multi-View Synthesis module improves pedestrian orientation estimation when integrated into the AVOD-FPN 3D detector, outperforming prior methods on KITTI Orientation, 3D, and Bird's Eye View benchmarks.
-
Towards Robust Surgical Automation via Digital Twin Representations from Foundation Models
Digital twin representations from vision foundation models enable LLM-based planning for robust peg transfer and gauze retrieval on the dVRK surgical platform with claimed generalizability.
-
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.