---
res:
  bibo_abstract:
  - Learning generative object models from unlabelled videos is a long standing problem
    and required for causal scene modeling. We decompose this problem into three easier
    subtasks, and provide candidate solutions for each of them. Inspired by the Common
    Fate Principle of Gestalt Psychology, we first extract (noisy) masks of moving
    objects via unsupervised motion segmentation. Second, generative models are trained
    on the masks of the background and the moving objects, respectively. Third, background
    and foreground models are combined in a conditional "dead leaves" scene model
    to sample novel scene configurations where occlusions and depth layering arise
    naturally. To evaluate the individual stages, we introduce the Fishbowl dataset
    positioned between complex real-world scenes and common object-centric benchmarks
    of simplistic objects. We show that our approach allows learning generative models
    that generalize beyond the occlusions present in the input videos, and represent
    scenes in a modular fashion that allows sampling plausible scenes outside the
    training distribution by permitting, for instance, object numbers or densities
    not observed in the training set.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Matthias
      foaf_name: Tangemann, Matthias
      foaf_surname: Tangemann
  - foaf_Person:
      foaf_givenName: Steffen
      foaf_name: Schneider, Steffen
      foaf_surname: Schneider
  - foaf_Person:
      foaf_givenName: Julius von
      foaf_name: Kügelgen, Julius von
      foaf_surname: Kügelgen
  - foaf_Person:
      foaf_givenName: Francesco
      foaf_name: Locatello, Francesco
      foaf_surname: Locatello
      foaf_workInfoHomepage: http://www.librecat.org/personId=26cfd52f-2483-11ee-8040-88983bcc06d4
    orcid: 0000-0002-4850-0683
  - foaf_Person:
      foaf_givenName: Peter
      foaf_name: Gehler, Peter
      foaf_surname: Gehler
  - foaf_Person:
      foaf_givenName: Thomas
      foaf_name: Brox, Thomas
      foaf_surname: Brox
  - foaf_Person:
      foaf_givenName: Matthias
      foaf_name: Kümmerer, Matthias
      foaf_surname: Kümmerer
  - foaf_Person:
      foaf_givenName: Matthias
      foaf_name: Bethge, Matthias
      foaf_surname: Bethge
  - foaf_Person:
      foaf_givenName: Bernhard
      foaf_name: Schölkopf, Bernhard
      foaf_surname: Schölkopf
  dct_date: 2023^xs_gYear
  dct_language: eng
  dct_title: Unsupervised object learning via common fate@
...
