Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention

• URL: http://arxiv.org/abs/2410.10774v1
• Date: Mon, 14 Oct 2024 17:46:32 GMT
• Title: Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
• Authors: Dejia Xu, Yifan Jiang, Chen Huang, Liangchen Song, Thorsten Gernoth, Liangliang Cao, Zhangyang Wang, Hao Tang,
• Abstract summary: Cavia is a novel framework for camera-controllable, multi-view video generation. Our framework extends the spatial and temporal attention modules, improving both viewpoint and temporal consistency. Cavia is the first of its kind that allows the user to specify distinct camera motion while obtaining object motion.
• Score: 62.2447324481159
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera control into the generation process, but their results are often limited to simple trajectories or lack the ability to generate consistent videos from multiple distinct camera paths for the same scene. To address these limitations, we introduce Cavia, a novel framework for camera-controllable, multi-view video generation, capable of converting an input image into multiple spatiotemporally consistent videos. Our framework extends the spatial and temporal attention modules into view-integrated attention modules, improving both viewpoint and temporal consistency. This flexible design allows for joint training with diverse curated data sources, including scene-level static videos, object-level synthetic multi-view dynamic videos, and real-world monocular dynamic videos. To our best knowledge, Cavia is the first of its kind that allows the user to precisely specify camera motion while obtaining object motion. Extensive experiments demonstrate that Cavia surpasses state-of-the-art methods in terms of geometric consistency and perceptual quality. Project Page: https://ir1d.github.io/Cavia/

Related papers

• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control [74.5434726968562]
  We tame transformers video for 3D camera control using a ControlNet-like conditioning mechanism based on Plucker coordinates. Our work is the first to enable camera control for transformer-based video diffusion models.
  arXiv  Detail & Related papers  (2024-07-17T17:59:05Z)
• Training-free Camera Control for Video Generation [19.526135830699882]
  We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Our method does not require any supervised finetuning on camera-annotated datasets or self-supervised training via data augmentation.
  arXiv  Detail & Related papers  (2024-06-14T15:33:00Z)
• CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation [117.16677556874278]
  We introduce CamCo, which allows fine-grained Camera pose Control for image-to-video generation. To enhance 3D consistency in the videos produced, we integrate an epipolar attention module in each attention block. Our experiments show that CamCo significantly improves 3D consistency and camera control capabilities compared to previous models.
  arXiv  Detail & Related papers  (2024-06-04T17:27:19Z)
• Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control [70.17137528953953]
  Collaborative video diffusion (CVD) is trained on top of a state-of-the-art camera-control module for video generation. CVD generates multiple videos rendered from different camera trajectories with significantly better consistency than baselines.
  arXiv  Detail & Related papers  (2024-05-27T17:58:01Z)
• Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis [43.02778060969546]
  We propose a controllable monocular dynamic view synthesis pipeline. Our model does not require depth as input, and does not explicitly model 3D scene geometry. We believe our framework can potentially unlock powerful applications in rich dynamic scene understanding, perception for robotics, and interactive 3D video viewing experiences for virtual reality.
  arXiv  Detail & Related papers  (2024-05-23T17:59:52Z)
• ControlVideo: Training-free Controllable Text-to-Video Generation [117.06302461557044]
  ControlVideo is a framework to enable natural and efficient text-to-video generation. It generates both short and long videos within several minutes using one NVIDIA 2080Ti.
  arXiv  Detail & Related papers  (2023-05-22T14:48:53Z)
• Playable Environments: Video Manipulation in Space and Time [98.0621309257937]
  We present Playable Environments - a new representation for interactive video generation and manipulation in space and time. With a single image at inference time, our novel framework allows the user to move objects in 3D while generating a video by providing a sequence of desired actions. Our method builds an environment state for each frame, which can be manipulated by our proposed action module and decoded back to the image space with volumetric rendering.
  arXiv  Detail & Related papers  (2022-03-03T18:51:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.