Boosting Camera Motion Control for Video Diffusion Transformers


Soon Yau Cheong (University of Surrey), Duygu Ceylan (Adobe Research), Armin Mustafa (University of Surrey), Andrew Gilbert (University of Surrey), Chun-Hao Paul Huang (Adobe Research)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Despite recent advancements in camera control methods for U-Net based video diffusion models, these methods have been shown to be ineffective for transformer-based diffusion models (DiT). In this paper, we investigate the underlying causes of this issue and propose solutions. Our study reveals that camera control performance depends heavily on the choice of conditioning methods, rather than on camera pose representations, as is commonly believed. To address the persistent motion degradation in DiT, we introduce Camera Motion Guidance (CMG), a classifier-free guidance approach that boosts camera motion by over 400%. Additionally, we present a sparse camera control pipeline that improves training data efficiency and simplifies the process of specifying camera poses for long videos. Project page at https://soon-yau.github.io/CameraMotionGuidance.

Citation

@inproceedings{Cheong_2025_BMVC,
author    = {Soon Yau Cheong and Duygu Ceylan and Armin Mustafa and Andrew Gilbert and Chun-Hao Paul Huang},
title     = {Boosting Camera Motion Control for Video Diffusion Transformers},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_753/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection