# Self-Supervised Visual Planning with Temporal Skip Connections

arXiv: https://arxiv.org/abs/1710.05268 · HTML: https://mlsanity.com/paper/1710.05268/

## Key facts

- Cited by 139 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2017.

## Built on by (most cited first, 30 of 139)

- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://mlsanity.com/paper/2205.09853/) (2022)
- [N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion](https://mlsanity.com/paper/2111.12417/) (2021)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2103.09504/) (2021)
- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [A Good Image Generator Is What You Need for High-Resolution Video Synthesis](https://mlsanity.com/paper/2104.15069/) (2021)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [Diffusion Models for Video Prediction and Infilling](https://mlsanity.com/paper/2206.07696/) (2022)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [Pathdreamer: A World Model for Indoor Navigation](https://mlsanity.com/paper/2105.08756/) (2021)
- [MaskViT: Masked Visual Pre-Training for Video Prediction](https://mlsanity.com/paper/2206.11894/) (2022)
- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [3D Neural Scene Representations for Visuomotor Control](https://mlsanity.com/paper/2107.04004/) (2021)
- [Rolling Diffusion Models](https://mlsanity.com/paper/2402.09470/) (2024)
- [FitVid: Overfitting in Pixel-Level Video Prediction](https://mlsanity.com/paper/2106.13195/) (2021)
- [Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction](https://mlsanity.com/paper/2103.04174/) (2021)
- [Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller](https://mlsanity.com/paper/1911.09676/) (2019)
- [CCVS: Context-aware Controllable Video Synthesis](https://mlsanity.com/paper/2107.08037/) (2021)
- [Playable Video Generation](https://mlsanity.com/paper/2101.12195/) (2021)
- [Learning Multi-Object Dynamics with Compositional Neural Radiance Fields](https://mlsanity.com/paper/2202.11855/) (2022)
- [Predicting Video with VQVAE](https://mlsanity.com/paper/2103.01950/) (2021)
- [Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos](https://mlsanity.com/paper/2407.16124/) (2024)
- [Efficient Video Prediction via Sparsely Conditioned Flow Matching](https://mlsanity.com/paper/2211.14575/) (2022)

## Abstract (arXiv)

In order to autonomously learn wide repertoires of complex skills, robots must be able to learn from their own autonomously collected data, without human supervision. One learning signal that is always available for autonomously collected data is prediction: if a robot can learn to predict the future, it can use this predictive model to take actions to produce desired outcomes, such as moving an object to a particular location. However, in complex open-world scenarios, designing a representation for prediction is difficult. In this work, we instead aim to enable self-supervised robotic learning through direct video prediction: instead of attempting to design a good representation, we directly predict what the robot will see next, and then use this model to achieve desired goals. A key challenge in video prediction for robotic manipulation is handling complex spatial arrangements such as occlusions. To that end, we introduce a video prediction model that can keep track of objects through occlusion by incorporating temporal skip-connections. Together with a novel planning criterion and action space formulation, we demonstrate that this model substantially outperforms prior work on video prediction-based control. Our results show manipulation of objects not seen during training, handling multiple objects, and pushing objects around obstructions. These results represent a significant advance in the range and complexity of skills that can be performed entirely with self-supervised robotic learning.