SynthRender and IRIS enable synthetic-data training that reaches 95-99% mAP@50 on real industrial object detection benchmarks across robotics and automotive settings.
Foundationpose: Unified 6d pose estimation and tracking of novel objects,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
A depth-augmented rigid pose refinement combined with a patient-specific statistical deformation model from NICP correspondences achieves 14.73 mm mean TRE for 3D-2D liver registration in controlled laparoscopic settings.
citing papers explorer
-
SynthRender and IRIS: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception
SynthRender and IRIS enable synthetic-data training that reaches 95-99% mAP@50 on real industrial object detection benchmarks across robotics and automotive settings.
-
Depth Augmented and FE Free 3D/2D Liver Registration for Laparoscopic Liver AR
A depth-augmented rigid pose refinement combined with a patient-specific statistical deformation model from NICP correspondences achieves 14.73 mm mean TRE for 3D-2D liver registration in controlled laparoscopic settings.