Zum Inhalt springen
KI-Atlas

Bild zu 3D und Rekonstruktion

3D-Struktur aus einem oder mehreren Fotos gewinnen

3DExperte #32
EingabeBild3D

Der vollständige Artikel liegt auf Englisch vor; Titel und Zusammenfassung sind lokalisiert.

WAS DIESE FÄHIGKEIT BEDEUTET

Takes one or several images and outputs a 3D representation — mesh, point cloud, depth map or renderable radiance field. With multiple views the geometry is constrained jointly by the parallax across photos and is more trustworthy; with a single image, unobserved parts can only be inferred from priors. Unlike text-to-3D both geometry and appearance are anchored by the input images.

Wie sie technisch umgesetzt wird

The multi-view route estimates camera poses, triangulates, and refines dense depth and surfaces; neural radiance fields encode the scene as a differentiable volumetric field aligned to input views by differentiable rendering, and 3D Gaussian splatting represents it as oriented translucent ellipsoids that render faster. Single-image routes rely on priors learned from large 3D datasets, or on score distillation from a 2D diffusion prior.

Repräsentative Produkte

3

Beteiligte Organisationen

Typische Verwendungen

  • Digital archiving of artefacts and buildings
  • Spatial perception for robots and driving
  • Turning product photos into 3D displays
  • Digital twins of real locations for film and games

Wie sie bewertet wird

Chamfer distance
Mean point distance between reconstructed and true surfaces
F-score
Balance of precision and recall within a distance threshold
Novel-view PSNR / SSIM
How close renderings from unseen views come to real photos

Grenzen und schwierige Punkte

  • Single-image reconstruction guesses entirely in unseen regions, and back surfaces appear invented once you rotate
  • Reflective, transparent and textureless surfaces are hard to match, and reconstruction fails broadly there
  • Output scale and metrics are inaccurate, so it cannot feed manufacturing or engineering measurement directly

Konzepte dahinter