CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers
This work addresses the need for controllable video generation for researchers and developers in generative AI, though it is incremental as it builds on existing multimodal transformers.
The paper tackled the problem of controlling video generation by incorporating 3D camera motion as a conditioning signal, achieving successful control and accurate camera path generation as verified by traditional computer vision methods.
We extend multimodal transformers to include 3D camera motion as a conditioning signal for the task of video generation. Generative video models are becoming increasingly powerful, thus focusing research efforts on methods of controlling the output of such models. We propose to add virtual 3D camera controls to generative video methods by conditioning generated video on an encoding of three-dimensional camera movement over the course of the generated video. Results demonstrate that we are (1) able to successfully control the camera during video generation, starting from a single frame and a camera signal, and (2) we demonstrate the accuracy of the generated 3D camera paths using traditional computer vision methods.