World-consistent Video Diffusion with Explicit 3D Modeling
qihang
Abstract
Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly generating 3D-consistent content. To address this, we propose World-consistent Video Diffusion (WVD), a novel framework that incorporates explicit 3D supervision using XYZ images, which encode global 3D coordinates for each image pixel. More specifically, we train a diffusion transformer to learn the joint distribution of RGB and XYZ frames. This approach supports multi-task adaptability via a flexible inpainting strategy. For example, WVD can estimate XYZ frames from ground-truth RGB or generate novel RGB frames using XYZ projections along a specified camera trajectory. In doing so, WVD unifies tasks like single-image-to-3D generation, multi-view stereo, and camera-controlled video generation. Our approach demonstrates competitive performance across multiple benchmarks, providing a scalable solution for 3D-consistent video and image generation with a single pretrained model.
Community
Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly generating 3D-consistent content. To address this, we propose World-consistent Video Diffusion (WVD), a novel framework that incorporates explicit 3D supervision using XYZ images, which encode global 3D coordinates for each image pixel. More specifically, we train a diffusion transformer to learn the joint distribution of RGB and XYZ frames. This approach supports multi-task adaptability via a flexible inpainting strategy. For example, WVD can estimate XYZ frames from ground-truth RGB or generate novel RGB frames using XYZ projections along a specified camera trajectory. In doing so, WVD unifies tasks like single-image-to-3D generation, multi-view stereo, and camera-controlled video generation. Our approach demonstrates competitive performance across multiple benchmarks, providing a scalable solution for 3D-consistent video and image generation with a single pretrained model.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (2024)
- MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model (2024)
- VistaDream: Sampling multiview consistent images for single-view scene reconstruction (2024)
- LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images (2024)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (2024)
- SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input (2024)
- DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper