# Context-free Self-Conditioned GAN for Trajectory Forecasting

arXiv: https://arxiv.org/abs/2603.08658 · HTML: https://mlsanity.com/paper/2603.08658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints](https://mlsanity.com/paper/1806.01482/) (2018)
- [Human Motion Trajectory Prediction: A Survey](https://mlsanity.com/paper/1905.06113/) (2019)
- [Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks](https://mlsanity.com/paper/1907.03395/) (2019)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [Human Trajectory Forecasting in Crowds: A Deep Learning Perspective](https://mlsanity.com/paper/2007.03639/) (2020)
- [Reconstruction Network for Video Captioning](https://mlsanity.com/paper/1803.11438/) (2018)
- [What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction](https://mlsanity.com/paper/1903.07933/) (2019)
- [Conditional Generative Neural System for Probabilistic Trajectory Prediction](https://mlsanity.com/paper/1905.01631/) (2019)
- [ClusterGAN : Latent Space Clustering in Generative Adversarial Networks](https://mlsanity.com/paper/1809.03627/) (2018)
- [Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation](https://mlsanity.com/paper/2010.01114/) (2020)
- [Diverse Image Generation via Self-Conditioned GANs](https://mlsanity.com/paper/2006.10728/) (2020)
- [Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step](https://mlsanity.com/paper/1710.08446/) (2017)
- [TH"OR: Human-Robot Navigation Data Collection and Accurate Motion Trajectories Dataset](https://mlsanity.com/paper/1909.04403/) (2019)
- [Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs](https://mlsanity.com/paper/1912.01118/) (2019)
- [RNN-based Pedestrian Crossing Prediction using Activity and Pose-related Features](https://mlsanity.com/paper/2008.11647/) (2020)
- [A survey on trajectory clustering analysis](https://mlsanity.com/paper/1802.06971/) (2018)
- [Generating Reliable and Efficient Predictions of Human Motion: A Promising Encounter between Physics and Neural Networks](https://mlsanity.com/paper/2006.08429/) (2020)

## Abstract (arXiv)

In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.