Перейти к содержимому
Атлас ИИ

Изображение в 3D и реконструкция

Восстановить трёхмерную структуру по одному или нескольким снимкам

3DЭкспертный #32
входИзображение3D

Полный текст статьи представлен на английском; заголовок и аннотация локализованы.

ЧТО ЭТО ЗА ВОЗМОЖНОСТЬ

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.

Как это устроено

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.

Примеры продуктов

3

Связанные организации

Типичное применение

  • 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

Как её оценивают

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

Границы и трудности

  • 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

Концепции в основе