Consistent Generative Query Networks

Abstract

Stochastic video prediction models take in a sequence of image frames, and generate a sequence of consecutive future image frames. These models typically generate future frames in an autoregressive fashion, which is slow and requires the input and output frames to be consecutive. We introduce a model that overcomes these drawbacks by generating a latent representation from an arbitrary set of frames that can then be used to simultaneously and efficiently sample temporally consistent frames at arbitrary time-points. For example, our model can "jump" and directly sample frames at the end of the video, without sampling intermediate frames. Synthetic video evaluations confirm substantial gains in speed and functionality without loss in fidelity. We also apply our framework to a 3D scene reconstruction dataset. Here, our model is conditioned on camera location and can sample consistent sets of images for what an occluded region of a 3D scene might look like, even if there are multiple possibilities for what that region might contain. Reconstructions and videos are available at https://bit.ly/2O4Pc4R.

References in corpus (5)

• Auto-Encoding Variational Bayes
• Unsupervised Learning of Video Representations using LSTMs
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• One-Shot Generalization in Deep Generative Models
• Learning and Querying Fast Generative Models for Reinforcement Learning

Cited by in corpus (10)

• Attentive Neural Processes
• Recurrent Attentive Neural Process for Sequential Data
• Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
• Active Feature Acquisition with Generative Surrogate Models
• S2RMs: Spatially Structured Recurrent Modules
• Environment Predictive Coding for Embodied Agents
• Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
• Physical world assistive signals for deep neural network classifiers -- neither defense nor attack
• Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe
• Robustifying Sequential Neural Processes