PanoWorld: Real-World Panoramic Generation

Published
Source
arXiv
Paper number
596
Field
Computer Vision
arXiv ID
2607.09661

Key points

  • It uses the rotational equivariance of panoramic ERP to treat rotation as a geometric transform and model only translation explicitly.
  • DPRC uses dense conditioning on panorama rays for accurate motion control, and GMA uses geometry-aware memory augmentation to maintain scene persistence.
  • The World360 dataset contains 70K real UAV clips and 50K AirSim360 simulation clips, including multi-altitude flight trajectories.
  • Compared with Matrix-3D, it improves FID from 27.64 to 16.93 at 720p, and it improves PSNR trajectory accuracy by 2 to 4 points.
  • Real-time generation with causal forcing produces 161 frames in 8 seconds on a single H20 GPU, versus about 4 minutes and 48 seconds previously.
  • A three-stage training pipeline progressively optimizes modeling, memory, and control.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)