Converting RGB videos into event-like temporal gradients lets an imitation agent ignore appearance differences between expert and learner domains, improving robustness without data augmentation.
The organization of the retina and visual system,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos
Converting RGB videos into event-like temporal gradients lets an imitation agent ignore appearance differences between expert and learner domains, improving robustness without data augmentation.