Future prediction
39 papers with code • 0 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in Future prediction
Latest papers with no code
MemFlow: Optical Flow Estimation and Prediction with Memory
To this end, we present MemFlow, a real-time method for optical flow estimation and prediction with memory.
Future Predictive Success-or-Failure Classification for Long-Horizon Robotic Tasks
The key idea behind the proposed method is an end-to-end approach for determining whether the action plan can complete a given task instead of manually redesigning the conditions.
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimation by making it learn to predict the future at training.
Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians
In particular, we develop and integrate a 3D Spring-Mass model into 3D Gaussian kernels, enabling the reconstruction of the visual appearance, shape, and physical dynamics of the object.
A representation-learning game for classes of prediction tasks
We propose a game-based formulation for learning dimensionality-reducing representations of feature vectors, when only a prior knowledge on future prediction tasks is available.
Future Prediction Can be a Strong Evidence of Good History Representation in Partially Observable Environments
Then, our main contributions are two-fold: (a) we demonstrate that the performance of reinforcement learning is strongly correlated with the prediction accuracy of future observations in partially observable environments, and (b) our approach can significantly improve the overall end-to-end approach by preventing high-variance noisy signals from reinforcement learning objectives to influence the representation learning.
A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning
In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data.
EuLagNet: Eulerian Fluid Prediction with Lagrangian Dynamics
Accurately predicting the future fluid is important to extensive areas, such as meteorology, oceanology and aerodynamics.
A Note On Lookahead In Real Life And Computing
We present three well known algorithmic frameworks used in practice based on availability of input information such as offline, online and semi-online.
Inferring Hybrid Neural Fluid Fields from Videos
Specifically, to deal with visual ambiguities of fluid velocity, we introduce a set of physics-based losses that enforce inferring a physically plausible velocity field, which is divergence-free and drives the transport of density.