0

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

FUTURIST, a multimodal future semantic prediction method using a visual sequence transformer, achieves state-of-the-art performance in future semantic segmentation through efficient masked modeling and a VAE-free hierarchical tokenization process.

Year
2025
Venue
CVPR 2025 1
Authors
4
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2501.08303ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Semantic future prediction is important for autonomous systems navigating dynamic environments. This paper introduces FUTURIST, a method for multimodal future semantic prediction that uses a unified and efficient visual sequence transformer architecture. Our approach incorporates a multimodal masked visual modeling objective and a novel masking mechanism designed for multimodal training. This allows the model to effectively integrate visible information from various modalities, improving prediction accuracy. Additionally, we propose a VAE-free hierarchical tokenization process, which reduces computational complexity, streamlines the training pipeline, and enables end-to-end training with high-resolution, multimodal inputs. We validate FUTURIST on the Cityscapes dataset, demonstrating state-of-the-art performance in future semantic segmentation for both short- and mid-term forecasting. We provide the implementation code at https://github.com/Sta8is/FUTURIST .

Authors

4