Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

Efstathios Karypidis; Ioannis Kakogeorgiou; Spyros Gidaris; Nikos Komodakis

doi:10.1109/cvpr52734.2025.00359

CVPR2025Top-tier venue

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis

DOI Publisher

2025Year

2Top-tier citations

Abstract

5 IACM-Forth Inputs Predictions Oracle Figure 1. Our framework predicts future semantic segmentation and depth maps using a multimodal transformer architecture. Leveraging masked visual modeling and cross-modal fusion, it excels in future semantic prediction, achieving state-of-the-art results in both tasks.