AI RESEARCH
Human-level 3D shape perception emerges from multi-view learning
arXiv CS.CV
•
ArXi:2602.17650v2 Announce Type: replace Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods have fallen short of human performance. Here we develop a modeling framework that predicts human 3D shape inferences for arbitrary objects, directly from experimental stimuli.