GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking
This work addresses a significant limitation in video generation models for creative video production by enabling advanced cinematic effects like multi-camera shooting and dolly zoom, though it builds incrementally on existing techniques like Gaussian splatting and Diffusion Transformers.
The paper tackles the problem of 4D video control in video generation, which is unsupported by existing methods, by proposing GS-DiT, a framework that uses pseudo 4D Gaussian fields with efficient dense 3D point tracking to generate videos with dynamic content adhering to different camera parameters, achieving a two-orders-of-magnitude speedup in inference compared to the state-of-the-art method.
4D video control is essential in video generation as it enables the use of sophisticated lens techniques, such as multi-camera shooting and dolly zoom, which are currently unsupported by existing methods. Training a video Diffusion Transformer (DiT) directly to control 4D content requires expensive multi-view videos. Inspired by Monocular Dynamic novel View Synthesis (MDVS) that optimizes a 4D representation and renders videos according to different 4D elements, such as camera pose and object motion editing, we bring pseudo 4D Gaussian fields to video generation. Specifically, we propose a novel framework that constructs a pseudo 4D Gaussian field with dense 3D point tracking and renders the Gaussian field for all video frames. Then we finetune a pretrained DiT to generate videos following the guidance of the rendered video, dubbed as GS-DiT. To boost the training of the GS-DiT, we also propose an efficient Dense 3D Point Tracking (D3D-PT) method for the pseudo 4D Gaussian field construction. Our D3D-PT outperforms SpatialTracker, the state-of-the-art sparse 3D point tracking method, in accuracy and accelerates the inference speed by two orders of magnitude. During the inference stage, GS-DiT can generate videos with the same dynamic content while adhering to different camera parameters, addressing a significant limitation of current video generation models. GS-DiT demonstrates strong generalization capabilities and extends the 4D controllability of Gaussian splatting to video generation beyond just camera poses. It supports advanced cinematic effects through the manipulation of the Gaussian field and camera intrinsics, making it a powerful tool for creative video production. Demos are available at https://wkbian.github.io/Projects/GS-DiT/.