Compositional Video Prediction

Ye et al., 2019

Summary

  • Method for solving pixel-level future prediction given a single image
  • Decompose scene into distinct entities that undergo motion and possibly interact
  • Generates realistic predictions for stacked objects and human activities in gyms
  • Links: [ website ] [ pdf ]

Background

  • Given a single image, humans can easily understand the scene and make predictions
  • Many other works also model relationships between objects, but do some combination of:
    • Use only simple visual stimuli
    • Use state based input
    • Rely on sequence of inputs
    • Don’t make predictions in pixel space

Methods

  • Given starting frame $f^0$ and the location of $N$ entities $\{b^0_n\}^N_{n=1}$, predict $T$ future frames $f^1, f^2, \dots, f^T$
  • Use entity predictor $\mathcal{P}$ for per-entity representations $\{x^t_n\}^N_{n=1}$
    • $\{x^{t+1}_n\} \equiv \mathcal{P}(\{x^t_n\}, z_t)$
    • $\{x^t_n\}^N_{n=1} \equiv \{(b^t_n, a^t_n)\}^N_{n=1}$
    • $b^t_n$ is the predicted location
    • $a^t_n$ is the predicted implicit features for entity appearance
      • $a^0_n$ obtained using ResNet-18 on cropped region from $f^0$
    • Interaction between entities modeled with graph neural network, edges are predetermined
  • Use frame decoder $\mathcal{D}$ to infer pixels
    • $f^t \equiv \mathcal{D}(\{x^t_n\},f^0)$
    • Warp normalized spatial representation to image coordinates with predicted location for each entity
    • Use soft masking for each entity to account for possible occlusions
    • Add these masked features to features from initial frame $f^0$
  • Single random latent variable $u$ to capture multi-modality of prediction task
    • Yields per-timestep latent variables $z_t$, which are correlated accross time, via a learned LSTM
  • Loss consists of three terms:
    • Prediction: $l_1$ loss on decoded frame from predicted features and $l_2$ loss on predicted location
    • Encoder: information bottleneck on latent variable distribution
    • Decoder: $l_1$ loss on decoded frame from features extracted from the same frame (auto-encoding loss)

Results

  • Datasets:
    • ShapeStacks: synthetic dataset of stacked objects that fall, different block shapes/colors and configurations
    • Penn Action: real video dataset of people playing indoor/outdoor sports, annotated with joint locations
      • Use gym activities subset: less camera motion, more similar backgrounds
  • Metrics:
    • Average MSE for entity locations
    • Learned Perceptual Image Patch Similarity (LPIPS) for generated frames
    • Due to stochasticity from random variable $u$, use best scores from 100 samples
  • Baselines:
    • No-Factor: only predicts at the level of frames
    • No-Edge: no interaction among entities
    • Pose Knows: also predicts poses as intermediate representation, predicts location but not appearance, no interactions
  • Proposed method consistenly performs better than the simple baselines on ShapeStacks, but No-Edge is a fairly close second
  • Adding adversarial loss, from Pose Knows, greatly improves performance of proposed method on Penn Action
  • Qualitative results on Penn Action are generally not that convincing for any model

Conclusion

  • Relies on supervision of entity locations and graph structure
  • Inclusion of latent variable to model multi-modality is interesting
    • Better metrics for evaluating diversity and accuracy would be useful
  • Poor performance on real world dataset suggests there is still a lot of room for improvement
Elias Z. Wang
Elias Z. Wang
AI Researcher | PhD Candidate