이미지-3D 생성과 3차원 재구성
한 장 또는 여러 장의 사진에서 3차원 구조를 복원한다
이 페이지의 본문은 영어로 제공됩니다. 제목과 요약은 한국어로 번역되었습니다.
이 능력이 뜻하는 것
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.
기술적으로 구현하는 방법
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.
대표 제품
3관련 기관
대표적 용도
- 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
성능을 평가하는 방법
- 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
경계와 난점
- 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