# T3VIP: Transformation-based 3D Video Prediction

arXiv: https://arxiv.org/abs/2209.11693 · HTML: https://mlsanity.com/paper/2209.11693/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 30 of 32)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [BOHB: Robust and Efficient Hyperparameter Optimization at Scale](https://mlsanity.com/paper/1807.01774/) (2018)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [Unsupervised Learning for Physical Interaction through Video Prediction](https://mlsanity.com/paper/1605.07157/) (2016)
- [Stochastic Variational Video Prediction](https://mlsanity.com/paper/1710.11252/) (2017)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [A System for Massively Parallel Hyperparameter Tuning](https://mlsanity.com/paper/1810.05934/) (2018)
- [Stochastic Adversarial Video Prediction](https://mlsanity.com/paper/1804.01523/) (2018)
- [Self-Supervised Visual Planning with Temporal Skip Connections](https://mlsanity.com/paper/1710.05268/) (2017)
- [Sample-efficient Cross-Entropy Method for Real-time Planning](https://mlsanity.com/paper/2008.06389/) (2020)
- [On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning](https://mlsanity.com/paper/2102.13651/) (2021)
- [Reasoning About Physical Interactions with Object-Oriented Prediction and Planning](https://mlsanity.com/paper/1812.10972/) (2018)
- [SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks](https://mlsanity.com/paper/1606.02378/) (2016)
- [Model-Based Visual Planning with Self-Supervised Functional Distances](https://mlsanity.com/paper/2012.15373/) (2020)
- [Learning 3D Dynamic Scene Representations for Robot Manipulation](https://mlsanity.com/paper/2011.01968/) (2020)
- [Few-Shot Goal Inference for Visuomotor Learning and Planning](https://mlsanity.com/paper/1810.00482/) (2018)
- [Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images](https://mlsanity.com/paper/1511.04048/) (2015)
- ["What happens if..." Learning to Predict the Effect of Forces in Images](https://mlsanity.com/paper/1603.05600/) (2016)
- [Experience-Embedded Visual Foresight](https://mlsanity.com/paper/1911.05071/) (2019)
- [Interpretable Intuitive Physics Model](https://mlsanity.com/paper/1808.10002/) (2018)

## Built on by (most cited first, 1 of 1)

- [Robot Skill Generalization via Keypoint Integrated Soft Actor-Critic Gaussian Mixture Models](https://mlsanity.com/paper/2310.15059/) (2023)

## Abstract (arXiv)

For autonomous skill acquisition, robots have to learn about the physical rules governing the 3D world dynamics from their own past experience to predict and reason about plausible future outcomes. To this end, we propose a transformation-based 3D video prediction (T3VIP) approach that explicitly models the 3D motion by decomposing a scene into its object parts and predicting their corresponding rigid transformations. Our model is fully unsupervised, captures the stochastic nature of the real world, and the observational cues in image and point cloud domains constitute its learning signals. To fully leverage all the 2D and 3D observational signals, we equip our model with automatic hyperparameter optimization (HPO) to interpret the best way of learning from them. To the best of our knowledge, our model is the first generative model that provides an RGB-D video prediction of the future for a static camera. Our extensive evaluation with simulated and real-world datasets demonstrates that our formulation leads to interpretable 3D models that predict future depth videos while achieving on-par performance with 2D models on RGB video prediction. Moreover, we demonstrate that our model outperforms 2D baselines on visuomotor control. Videos, code, dataset, and pre-trained models are available at http://t3vip.cs.uni-freiburg.de.