One Image is inherently ambiguousMulti-view stereo reconstruction (MVS)We need multi view geometryDepth EstimationsLOTUSDepth AnythingSMERFNeRFMarigoldMonocular Depth EstimationLLFFDinoV2NeuralangeloCOLMAPDUSt3RRadSplatMarigoldDepthProMASt3R-SLAM Depth Estimation NotionGaussian SplattingError MapPinhole Camera ModelTriangulationTwo-view Geometry4D EstimationRadiance FieldsSDF impressive demoGenerating WorldsToday we're sharing our first step towards spatial intelligence: an AI system that generates 3D worlds from a single image.https://www.worldlabs.ai/blogdatasetNYU Depth V2 « Nathan SilbermanSamples of the RGB image, the raw depth image, and the class labels from the dataset.https://cs.nyu.edu/~fergus/datasets/nyu_depth_v2.html