Research map / Video / Video segmentation and tracking
Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace deterministic/standard regression with probabilistic VAE-based motion prior (cross convolutional VAE) for zero-shot analogy-making | Visual analogy-making on sprites · Sprites analogy test set | mean squared pixel error: 15.9 vs 23.0 for best baseline (Dis + Cls) | Helped |
| Remove VAE KL term and sampling (plain autoencoder) on shape dataset (ablation) | Cross convolutional network on 2D shapes · 2D shapes velocity distribution | match to ground-truth velocity distribution | Hurt |
Closest papers by meaning
- Generating Videos with Scene Dynamics (NeurIPS 2016 · similarity 0.88)
- Decomposing Motion and Content for Natural Video Sequence Prediction (ICLR 2017 · similarity 0.87)
- Temporal Coherency based Criteria for Predicting Video Frames using Deep Multi-stage Generative Adversarial Networks (NeurIPS 2017 · similarity 0.87)
- Visual Representation Learning with Stochastic Frame Prediction (ICML 2024 · similarity 0.87)
- Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation (ICLR 2025 · similarity 0.86)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.