AH36M (Ambiguous Human3.6M)
Introduced by Biggs et al. in 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data
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.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
AH36M
|
MHEntropy
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
