Personal tools
You are here: Home Events ANC Workshop: Lukasz Romaszko, Chair: George Papamakarios

ANC Workshop: Lukasz Romaszko, Chair: George Papamakarios

— filed under:

  • ANC Workshop Talk
When Apr 03, 2018
from 11:00 AM to 12:00 PM
Where IF 4.31/4.33
Add event to calendar vCal

Obtaining a Rich 3D Explanation of a Scene from a Single Image 

We develop an inverse graphics approach to the problem of scene
understanding, obtaining a rich representation that includes
descriptions of the objects in the scene and their spatial layout, as
well as global latent variables like the camera parameters and
lighting. The framework’s stages include object detection, the
prediction of the camera and lighting variables, and prediction of
object-specific variables (shape, appearance and pose). This acts like
the encoder of an autoencoder, with graphics rendering as the
decoder. Importantly the scene representation is interpretable and is
of variable dimension to match the detected number of objects plus the
global variables. For the prediction of the camera latent variables we
introduce a novel architecture termed Probabilistic HoughNets (PHNs),
which provides a principled approach to combining information from
multiple detections. We demonstrate the quality of the reconstructions
obtained quantitatively on synthetic data, and qualitatively on real scenes.