DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
This work addresses the challenge of creating detailed 3D and 4D scenes from minimal input for applications in computer vision and graphics, representing a novel method rather than an incremental improvement.
The paper tackles the problem of generating photorealistic 3D and 4D scenes from a single image by proposing DimensionX, a framework that uses controllable video diffusion to overcome limitations in spatial and temporal controllability, achieving superior results in experiments compared to previous methods.
In this paper, we introduce \textbf{DimensionX}, a framework designed to generate photorealistic 3D and 4D scenes from just a single image with video diffusion. Our approach begins with the insight that both the spatial structure of a 3D scene and the temporal evolution of a 4D scene can be effectively represented through sequences of video frames. While recent video diffusion models have shown remarkable success in producing vivid visuals, they face limitations in directly recovering 3D/4D scenes due to limited spatial and temporal controllability during generation. To overcome this, we propose ST-Director, which decouples spatial and temporal factors in video diffusion by learning dimension-aware LoRAs from dimension-variant data. This controllable video diffusion approach enables precise manipulation of spatial structure and temporal dynamics, allowing us to reconstruct both 3D and 4D representations from sequential frames with the combination of spatial and temporal dimensions. Additionally, to bridge the gap between generated videos and real-world scenes, we introduce a trajectory-aware mechanism for 3D generation and an identity-preserving denoising strategy for 4D generation. Extensive experiments on various real-world and synthetic datasets demonstrate that DimensionX achieves superior results in controllable video generation, as well as in 3D and 4D scene generation, compared with previous methods.