A neural re-simulation system corrects noisy single-image depth simulations to produce visually plausible multi-bounce ball trajectories in still images.
Learning A Physical Long-term Predictor
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Evolution has resulted in highly developed abilities in many natural intelligences to quickly and accurately predict mechanical phenomena. Humans have successfully developed laws of physics to abstract and model such mechanical phenomena. In the context of artificial intelligence, a recent line of work has focused on estimating physical parameters based on sensory data and use them in physical simulators to make long-term predictions. In contrast, we investigate the effectiveness of a single neural network for end-to-end long-term prediction of mechanical phenomena. Based on extensive evaluation, we demonstrate that such networks can outperform alternate approaches having even access to ground-truth physical simulators, especially when some physical parameters are unobserved or not known a-priori. Further, our network outputs a distribution of outcomes to capture the inherent uncertainty in the data. Our approach demonstrates for the first time the possibility of making actionable long-term predictions from sensor data without requiring to explicitly model the underlying physical laws.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural Re-Simulation for Generating Bounces in Single Images
A neural re-simulation system corrects noisy single-image depth simulations to produce visually plausible multi-bounce ball trajectories in still images.