Building Rome from a Single Image

Key points

• While pretrained 3D object generators encode a strong shape prior, they are mainly designed for isolated objects in a fixed canonical volume and focus mostly on indoor scenes, since diverse 3D data for outdoor scenes are quite limited.1
• In this work, we present a method that redesigns such an object-centric generator, e.g., Trellis 2, to work on both indoor and outdoor scenes while retaining its prior.1
• Experiments on Tanks and Temples, ScanNet++, and in-the-wild images show that our method outperforms all baselines in geometric accuracy and perceptual quality across both indoor and outdoor scenes.1

Sources (1)

• [1]Building Rome from a Single Image
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:59 PM

  Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe.

  While pretrained 3D object generators encode a strong shape prior, they are mainly designed for isolated objects in a fixed canonical volume and focus mostly on indoor scenes, since diverse 3D data for outdoor scenes are quite limited.

Extractive summary: sentences quoted from the sources.