Section: Partnerships and Cooperations

International Initiatives

Inria@SiliconValley

Associate Team involved in the International Lab:

CRISP2

• Title: Creating and Rendering Images based on the Study of Perception

• International Partner (Institution - Laboratory - Researcher):

  • University of California Berkeley (United States) - Electrical Engineering and Computer Science Department (EECS) - Maneesh Agrawala

• Start year: 2014

• See also: http://www-sop.inria.fr/reves/crisp/

• The CRISP collaboration aims at developing novel techniques to create and manipulate effective numerical imagery. We adopt a multidisciplinary approach, focusing on understanding how people create and perceive images, on developing new rendering algorithms based on this understanding, and on building interactive tools that enable users to efficiently produce the images they have in mind. The participants of CRISP share complementary expertise in computer graphics, human computer interaction and human visual perception.

  In 2015 we published two papers in the Computer Graphics Forum journal, which were presented at the Eurographics Symposium on Rendering (EGSR). In the first paper we used a model of texture similarity to transfer seasons between photographs . Our algorithm predicts how to change colors and textures in an image to give it the seasonal appearance of another image. In particular, our method captures season-related effects such as leaves on trees, snow and flooding. This work was done in collaboration with Alexei Efros who is an expert in data-driven image manipulation.

  The second paper contributes to more traditional, physically-based rendering using bidirectional path tracing . The key idea behind our approach is to exploit combinatorial explosion to cheaply construct a set of light paths as the Cartesian product of the eye and light sub-paths. The novelty of our work is to approximate the contribution of these paths in a probabilistic manner, without constructing each path in the set explicitly. This work results from collaboration with Ravi Ramamoorthi.

  We are currently focusing our efforts on two core topics of the CRISP collaboration: perceptual rendering and plausible image-based rendering. In particular, we plan to explore several projects related to the perception and rendering of stereo images. This research will greatly benefit from an Inria postdoc, George Koulieris, who will share his time between Inria and UC Berkeley. In addition, Martin S. Banks from UC Berkeley plans to spend part of his sabbatical at Inria.

  CRISP has resulted in two publications this year with Aloyha Efros [9] and R. Ramammoorthi [10] .

United States. We have several collaborations with Adobe Research. We worked on jewelry design [8] with Wilmot Li, who hosted Emmanuel Iarussi for an 3-months internship. We also work with Eli Shechtman and Sylvain Paris in the context of the multi-view inpainting project of T. Thonat. We collaborate with F. Durand from MIT in the context of the global illumination project [10] . We collaborate with Daniel Aliaga from Purdue University on sketch-based procedural modeling.

Greece. We collaborate with the Technical University of Crete in the context of the project on attention and Virtual Reality (G. Koulieris).