Single-View 3D Reconstruction

Single-view 3D reconstruction estimates geometry and appearance from one image, where hidden surfaces, depth, and object relationships are inherently ambiguous. Methods represent outputs as meshes, point clouds, neural fields, or 3D Gaussians, using feed-forward prediction, parametric shape models, differentiable rendering, and diffusion or video-generation priors to infer unseen views. Work spans objects, indoor scenes, humans and animals, and specialized settings such as medical imaging and CAD; physical constraints and explicit image-to-geometry alignment increasingly support editable or simulation-ready results. The central tension is that generative priors can produce complete, plausible outputs but may hallucinate details or drift from the input, so geometry, identity, cross-view consistency, speed, and uncertainty remain important evaluation challenges.