RESEARCH PAPER

MoVieDrive: Urban Scene Synthesis with Multi-Modal Multi-View Video Diffusion Transformer

Guile Wu; David Huang; Dongfeng Bai; Bingbing Liu

Classification

View four quadrants
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. MoVieDrive specializes video diffusion for layout-conditioned multi-camera RGB, depth and semantic generation in driving. Its structural controls are inputs and it has no executed-control or action-selection pathway. This is learned driving-scene simulation, not a general video backbone. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX