Perception Through Structured Generative Models Call for Papers

We are organizing a workshop at ECCV, all about the importance of structured generative models in perception. If you have some work on this topic, consider submitting a short 4-page paper here. The deadline is August 20. Also we have a great lineup of invited speakers, so if you are attending ECCV you should drop into our zoom session on August 28.


CFP: ECCV 2020 Workshop: Perception Through Structured Generative Models 

August 28, 2020


The highly structured nature of the visual world has inspired many
computer vision researchers to pursue an analysis-by-synthesis
approach: to understand an image, one should be able to reproduce it
with a model. A good model should also be able to extrapolate into
unseen space or time: given a 2D or 2.5D image of a partially occluded
object, what is the full 3D extent? Given a fragment of a video, how
does the remainder play out? Generative models of images, video, and
3D data have made great strides in recent years, but their utility as
causal or interpretable models has not always advanced in step. For
example, while GANs can currently generate beautiful images, they do
not necessarily learn a latent space of graphics-like or
semantically-interpretable elements. In this workshop, we aim to
explore how generative models can facilitate perception, and in
particular, how to design and use structured generative models (of
images, video, and 3D data) for computer vision inference

We are soliciting original contributions in computer vision, robotics,
and machine learning relating to the following topics:

    Inverse graphics

    Generative models for images, video, 3D data

    Reconstruction or prediction as objectives for representation learning

    Learning disentangled and/or interpretable representations

    Novel methods for structured generative modelling

    Generation for prediction, anomaly detection, compression, search, etc. 

    Incorporating hierarchy and graphics-like elements into machine learning

    Causal and forward models of visual data

Submission deadline: August 20

Submissions should be 4 pages long, including references. The 4-page
limit helps eliminate dual-submission conflicts with ECCV and other
conferences. (E.g., even papers accepted to ECCV may be dual-submitted
here, provided that they are shortened to 4 pages.)

The workshop organizers will review the papers in a single-blind
fashion. All accepted papers will be included in a poster presentation
session. Accepted papers will be published in the proceedings.


    Adam Harley (CMU)

    Katerina Fragkiadaki (CMU)

    Shubham Tulsiani (FAIR)

Email Adam with questions (, and see the website for
more info on the workshop: