Andrea Vedaldi, David Novotny, Benjamin Biggs, Sébastien Ehrhardt, Hanbyul Joo, Benjamin Graham
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we aim at recovering several plausible reconstructions compatible with the input data. We suggest that ambiguities can be modelled more effectively by parametrizing the possible body shapes and poses via a suitable 3D model, such as SMPL for humans. We propose to learn a multi-hypothesis neural network regressor using a best-of-M loss, where each of the M hypotheses is constrained to lie on a manifold of plausible human poses by means of a generative model. We show that our method outperforms alternative approaches in ambiguous pose recovery on standard benchmarks for 3D humans, and in heavily occluded versions of these benchmarks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2011.00980")
get_code_for_paper("2011.00980")
have("2011.00980")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2011.00980.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2011.00980)
Connect an agent — have() is free.