Here we introduce an approximated differentiable renderer to refine a 6-DoF pose prediction using only 2D alignment information. To this end, a two-branched convolutional encoder network is employed to jointly estimate the object class and its 6-DoF pose in the scene. We then propose a new formulation of an approximated differentiable renderer to re-project the 3D object on the image according to its predicted pose; in this way the alignment error between the observed and the re-projected object silhouette can be measured. Since the renderer is differentiable, it is possible to back-propagate through it to correct the estimated pose at test time in an online learning fashion. Eventually we show how to leverage the classification branch to profitably re-project a representative model of the predicted class (i.e. a medoid) instead. Each object in the scene is processed independently and novel viewpoints in which both objects arrangement and mutual pose are preserved can be rendered. Differentiable renderer code is available at:https://github.com/ndrplz/tensorflow-mesh-renderer.
End-to-end 6-DoF Object Pose Estimation through Differentiable Rasterization / Palazzi, Andrea; Bergamini, Luca; Calderara, Simone; Cucchiara, Rita. - (2019), pp. 702-715. ((Intervento presentato al convegno Second Workshop on 3D Reconstruction Meets Semantics (3DRMS) tenutosi a Munich, Germany nel 8 - 14 September 2018.
Data di pubblicazione: | 2019 |
Data di prima pubblicazione: | 23-gen-2019 |
Titolo: | End-to-end 6-DoF Object Pose Estimation through Differentiable Rasterization |
Autore/i: | Palazzi, Andrea; Bergamini, Luca; Calderara, Simone; Cucchiara, Rita |
Autore/i UNIMORE: | |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1007/978-3-030-11015-4_53 |
Codice identificativo Scopus: | 2-s2.0-85061710987 |
Codice identificativo ISI: | WOS:000594385100053 |
Nome del convegno: | Second Workshop on 3D Reconstruction Meets Semantics (3DRMS) |
Luogo del convegno: | Munich, Germany |
Data del convegno: | 8 - 14 September 2018 |
Serie: | LECTURE NOTES IN COMPUTER SCIENCE |
Pagina iniziale: | 702 |
Pagina finale: | 715 |
Citazione: | End-to-end 6-DoF Object Pose Estimation through Differentiable Rasterization / Palazzi, Andrea; Bergamini, Luca; Calderara, Simone; Cucchiara, Rita. - (2019), pp. 702-715. ((Intervento presentato al convegno Second Workshop on 3D Reconstruction Meets Semantics (3DRMS) tenutosi a Munich, Germany nel 8 - 14 September 2018. |
Tipologia | Relazione in Atti di Convegno |
File in questo prodotto:
File | Descrizione | Tipologia | |
---|---|---|---|
palazzi_eccvw.pdf | Post-print dell'autore (bozza post referaggio) | Open Access Visualizza/Apri |

I documenti presenti in Iris Unimore sono rilasciati con licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia, salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris