activity
20182020
most citedUnsupervised Video Decomposition using Spatio-temporal Iterative Inference

7 citations · 7 across the 1 of their papers we have counts for

collaborators

5 papers

cs.CV20207 cited

Unsupervised Video Decomposition using Spatio-temporal Iterative Inference

Polina Zablotskaia, Edoardo A. Dominici, Leonid Sigal +1

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to levera…

cs.CV2019

Generating Videos of Zero-Shot Compositions of Actions and Objects

Megha Nawhal, Mengyao Zhai, Andreas Lehrmann +2

Human activity videos involve rich, varied interactions between people and objects. In this paper we develop methods for generating such videos -- making progress toward addressing…

cs.GR2019

Neural Volumes: Learning Dynamic Renderable Volumes from Images

Stephen Lombardi, Tomas Simon, Jason Saragih +3

Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occ…

cs.CV2019

Learning Physics-guided Face Relighting under Directional Light

Thomas Nestmeyer, Jean-François Lalonde, Iain Matthews +1

Relighting is an essential step in realistically transferring objects from a captured image into another environment. For example, authentic telepresence in Augmented Reality requi…

cs.CV2018

Traversing the Continuous Spectrum of Image Retrieval with Deep Dynamic Models

Ziad Al-Halah, Andreas M. Lehrmann, Leonid Sigal

We introduce the first work to tackle the image retrieval problem as a continuous operation. While the proposed approaches in the literature can be roughly categorized into two mai…