Ilke Demir | SpeakerHub

Personal Details

Bio

Dr. Ilke Demir's research focuses on generative models for digitizing the real world, deepfake detection and generation techniques, content provenance and protection, analysis and synthesis approaches in geospatial ML, and computational geometry for synthesis and fabrication. Currently, she is a Senior Staff Research Scientist at Intel Labs, leading Intel's Trusted Media research and engineering teams.

Dr. Demir earned her Ph.D. and M.S. in Computer Science from Purdue University, and her B.S. in Computer Engineering from Middle East Technical University with a minor in Electrical Engineering. Her Ph.D. dissertation conceives geometric and topological shape processing approaches for reconstruction, modeling, and synthesis; which pioneered the area of proceduralization. Afterwards, Dr. Demir joined Facebook as a Postdoctoral Research Scientist, where their team developed the breakthrough innovation on generative street addresses.

At the intersection of art and science, Dr. Demir contributed to several animated feature and VR/AR short films in Pixar Animation Studios and Intel Studios, respectively. She established the research foundations of the world's largest volumetric capture studio at Intel, bridging the gap between the creative process and AI approaches. Prior to joining Intel, she had a brief startup experience (with a successful acquisition), and she was also a visiting scholar at UCLA.

In addition to her publications in top-tier venues, she has organized workshops, competitions, and courses in deep learning, computer vision, and graphics such as DeepGlobe, USM3D, WiCV, SUMO, DLGC, EarthVision, and OpenEDS, to name a few. Dr. Demir received numerous awards and honors such as ACM Distinguished Speaker, Jack Dangermond Award, Bilsland Dissertation Fellowship, and IEEE Industry Distinguished Lecturer, in addition to her best paper/poster/reviewer/tech awards. Her scientific articles received significant attention from researchers and media outlets around the world, such as CNN, BBC, The Independent, and Liberation. She has been invited to present over 120 talks and panels worldwide, on the wide range of topics that her work spans.

Dr. Demir has been actively involved in women in science organisms, always being an advocate for women and underrepresented minorities.

Current position (1)

Senior Staff Research Scientist

Intel

Degrees (3)

Computer Science, PhD

Purdue University

2010 to 2016

Computer Science, Ms

Purdue University

2010 to 2014

Computer Science, Bs

Middle East Technical University

2006 to 2010

Presentations

Presentations (3)

Embattling for a Deep Fake Dystopia

Recent advances in the democratization of AI have been enabling the widespread use of generative models, causing the exponential rise of fake content. As every technology is simultaneously built with its counterpart to neutralize it, this is the perfect time to fortify our eyes with deep fake detectors. Deep fakes depend on photorealism to disable our natural detectors: we cannot simply look at a video to decide if it is real. On the other hand, this realism is not preserved in physiological, biological, and physical signals of deep fakes, yet. My key assertion follows that such signals hidden in portrait videos can be used as an implicit descriptor of authenticity, like a generalizable watermark of humans, because they are neither spatially nor temporally preserved in deep fakes.

The Future of Filmmaking: AI for Volumetric Capture and Reconstruction

One picture is worth a thousand words, so what have been told with videos? What about 100 simultaneous videos to reconstruct every frame of life in a 10.000 sq. ft dome? Similar to other industries, entertainment industry is also being reshaped by AI, especially towards AR/VR consumption.

This talk will introduce deep learning advancements in 3D vision, reconstruction, and shape understanding with a focus on generative models. Then we will shift gears with an overview of such models in 3D, and their progression on voxels, point clouds, meshes, graphs, and other 3D representations. Back to our studio, in addition to a discussion about how to process such large visual data, the challenges of scaling 10x over current capture platforms, and over 200x over state-of-the-art datasets will be presented. The talk will conclude with a sneak peek of upcoming VR/AR productions from the world's largest volumetric capture stage at Intel Studios, as an example of real-world use cases.

The Science of Generative Architecture: Proceduralization

Manual creation of massive and detailed 3D models may take weeks, or months, even for experienced artists. In contrast, generative algorithms enable efficiently creating content coherent with the reality, as long as the representations are good approximations of the real world. In this talk, I will introduce "proceduralization" to discover such generative representations from 2D and 3D data for synthesis, modeling, and reconstruction; combining computer vision, machine learning, and computational geometry approaches. I will briefly introduce geometry processing algorithms to discover artistic elements, and grammar discovery methods to extract procedural rules. The rest of the talk will be devoted to proceduralization applications for content creation, interactive editing, localization, mapping, and reconstruction. I will conclude by how similar constructions can be exploited in extracting shape abstractions in the context of geometric deep learning.

Past talks (17)

Content Authenticity in the Age of Generative AI

International Copyright Technology Conference

Korea

November 6, 2024

Defenses Against Generative AI Misuse

TechCamp Korea

Korea

October 31, 2024

Embattling for a Deep Fake Dystopia

ACM Distinguished Speaker Lecture

New Jersey