Oriel — AI & technology worth noticing, every day.

WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control

Paper · https://arxiv.org/abs/2610.33135

Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius variation from arbitrary initial azimuths. Such viewpoint changes also reveal character regions unseen in the initial frame, causing geometric distortions, appearance degradation, and identity drift. To systematically study these coupled challenges, we introduce CLACT, a large-scale Character-centric dataset and benchmark covering diverse Large-Angle Camera Trajectories, with accurate camera geometry and multi-view character observations for training and evaluation. We further propose WorldCast, a framework for world-consistent character video generation under diverse large-angle camera motions. Specifically, we back-project the initial frame into a 3D point cloud using estimated depth, align the point-cloud scale with the target camera trajectory, and render it along the trajectory to obtain explicit geometric guidance and coverage masks. To complement the incomplete character information, we introduce Geometry-Aligned Memory Attention (GAMA). Using relative camera poses estimated jointly from the initial frame and multi-view character anchors, we express anchor and target-view geometry in a common coordinate frame. GAMA uses this geometric alignment to guide the retrieval and injection of view-relevant character features during generation. Evaluations across diverse large-angle camera trajectories demonstrate accurate trajectory following while preserving character geometry, appearance, and identity.

First seen by Oriel on .

AI summary

WorldCast generates character videos that follow large-angle camera trajectories while preserving character geometry, appearance, and identity.

  • The CLACT dataset and benchmark cover diverse large-angle camera trajectories with accurate camera geometry and multi-view character observations.
  • WorldCast back-projects the initial frame into a 3D point cloud, aligns its scale to the target trajectory, and renders geometric guidance and coverage masks.
  • Geometry-Aligned Memory Attention (GAMA) aligns anchor and target-view geometry in a common coordinate frame to retrieve and inject relevant character features.
  • Evaluations report accurate trajectory following across diverse camera motions while preserving character consistency.

#video generation #camera control #3d geometry #computer vision

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 55, latest observation ; +14 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 2, latest observation ; +1 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2610.33135https://arxiv.org/abs/2610.33135 Read discussion