Sta8is/FUTURIST

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

FUTURIST employs a multimodal visual sequence transformer to directly predict multiple future semantic modalities. We focus on two key modalities: semantic segmentation and depth estimation.

• Key innovation 1: We introduce a VAE-free hierarchical tokenization process integrated directly into our transformer. This simplifies training, reduces computational overhead, and enables true end-to-end optimization
• Key innovation 2: Our model features an efficient cross-modality fusion mechanism that improves predictions by learning synergies between different modalities (segmentation + depth)
• Key innovation 3: We developed a novel multimodal masked visual modeling objective specifically designed for future prediction tasks

We achieve state-of-the-art performance in future semantic segmentation on Cityscapes, with strong improvements in both short-term (0.18s) and mid-term (0.54s) predictions

Code

https://github.com/Sta8is/FUTURIST

Demo:

We provide 2 quick demos.

• 
• Demo.

Citation:

If you found Futurist useful in your research, please consider starring ⭐ us on GitHub and citing 📚 us in your research!

@InProceedings{Karypidis_2025_CVPR,
author = {Karypidis, Efstathios and Kakogeorgiou, Ioannis and Gidaris, Spyros and Komodakis, Nikos},
title = {Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {3793-3803}

@article{karypidis2025advancingsemanticfutureprediction,
      title={Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers}, 
      author={Efstathios Karypidis and Ioannis Kakogeorgiou and Spyros Gidaris and Nikos Komodakis},
      year={2025},
      journal={arXiv:2501.08303}
      url={https://arxiv.org/abs/2501.08303}, 
}