Pith. sign in

REVIEW 5 cited by

Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.17414 v1 pith:2NP7677F submitted 2024-05-27 cs.CV cs.GR

Zhengfei Kuang , Shengqu Cai , Hao He , Yinghao Xu , Hongsheng Li , Leonidas Guibas , Gordon Wetzstein This is my paper · ORCID
classification cs.CVcs.GR
keywords videogenerationcameratrajectoriesdifferentcollaborativeconsistencycontrol
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation process is an important goal moving forward and recent approaches that condition video generation models on camera trajectories make strides towards it. Yet, it remains challenging to generate a video of the same scene from multiple different camera trajectories. Solutions to this multi-video generation problem could enable large-scale 3D scene generation with editable camera trajectories, among other applications. We introduce collaborative video diffusion (CVD) as an important step towards this vision. The CVD framework includes a novel cross-video synchronization module that promotes consistency between corresponding frames of the same video rendered from different camera poses using an epipolar attention mechanism. 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, as shown in extensive experiments. Project page: https://collaborativevideodiffusion.github.io/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    Encoding cameras as pixel-aligned raxels lets one video diffusion model jointly denoise video and trajectories, supporting pose estimation, controlled generation, and joint synthesis.

  2. Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Vid-CamEdit re-synthesizes monocular videos along user-defined camera paths by conditioning a video diffusion model on 2D flows derived from estimated 3D geometry, without training on multi-view video data.

  3. FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A two-stage video diffusion pipeline uses optical flow as its control signal, achieving accurate camera control and natural object motion without ground-truth camera-parameter labels during training.

  4. RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control

    cs.CV 2025-02 conditional novelty 5.0 of 10

    Metric-scale depth alignment plus scene-constrained noise shaping improves camera controllability and video quality for image-to-video generation on RealEstate10K.

  5. Camera Trajectory Generation: A Comprehensive Survey of Methods, Metrics, and Future Directions

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A review that organizes camera trajectory generation into representation levels, algorithm families, evaluation metrics, and datasets.

Pith tools