paper-with-me

AH36M

Ambiguous Human3.6M

홈페이지 · 논문 6편

Since H36M is captured in a controlled environment, it rarely depicts challenging real-world scenarios such as body occlusions that are the main source of ambiguity in the single-view 3D shape estimation problem. Hence, we construct an adapted version of H36M with synthetically-generated occlusions by randomly hiding a subset of the 2D keypoints and re-computing an image crop around the remaining visible joints.

Images English

벤치마크

Multi-Hypotheses 3D Human Pose Estimation on AH36M 결과 40개