PolarVSR is the first unified architecture for continuous space-time polarization video reconstruction from DoFP captures, using polarization-aware implicit neural representations, a flow-guided variation loss, and a new large-scale benchmark.
6d object pose tracking in internet videos for robotic manipu- lation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
citing papers explorer
-
PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction
PolarVSR is the first unified architecture for continuous space-time polarization video reconstruction from DoFP captures, using polarization-aware implicit neural representations, a flow-guided variation loss, and a new large-scale benchmark.
-
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.