PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Published
Source
arXiv
Paper number
571
Field
Computer Vision
arXiv ID
2607.05373

Key points

  • It optimizes 3DGS directly in pixel space through differentiable rendering without VAE or RAE, eliminating information loss.
  • It unifies generation and reconstruction in a single forward pass by splitting views into clean and noisy subsets.
  • The geometry perception loss provides geometric supervision in the feature space of a 3D foundation model.
  • It outperforms existing latent-space generation methods on RealEstate10K, DL3DV-10K, and WorldScore, while matching state-of-the-art reconstruction quality.
  • Removing the geometry perception loss causes a 1.13 dB drop in PSNR and a 12.5 percent relative drop in AUC@5, confirming its effectiveness.

Paper links

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

Read original (opens in a new tab)