VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

TL;DR

This paper introduces a novel method for controlling camera movement in transformer-based video diffusion models, enabling fine-grained 3D camera control in generated videos, which was not possible with previous models.

Contribution

We propose a ControlNet-like conditioning mechanism with spatiotemporal camera embeddings for transformer-based video diffusion models, enabling controllable video generation.

Findings

Achieves state-of-the-art performance in controllable video generation.

First method to enable camera control in transformer-based video diffusion models.

Demonstrates effective fine-tuning on the RealEstate10K dataset.

Abstract

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applications related to content creation, visual effects, and 3D vision. Recently, new methods demonstrate the ability to generate videos with controllable camera poses these techniques leverage pre-trained U-Net-based diffusion models that explicitly disentangle spatial and temporal generation. Still, no existing approach enables camera control for new, transformer-based video diffusion models that process spatial and temporal information jointly. Here, we propose to tame video transformers for 3D camera control using a ControlNet-like conditioning mechanism that incorporates spatiotemporal camera embeddings based on Pl\"ucker coordinates. The approach demonstrates state-of-the-art performance for controllable video generation after fine-tuning on the RealEstate10K dataset. To the best of our knowledge, our work is the first to enable camera control for transformer-based video diffusion models.