Biometric verification
Face recognition, presentation attack and deepfake detection, document and identity checks. Benchmark accuracy is the easy part. What matters is behaviour when someone is actively trying to fool the model.
Computer vision · Research and applied AI · Indonesia
Williem
Half my work ends in a paper.
The other half ends in production.
Ph.D. in computer vision, publishing since 2012 on light field depth estimation and stereo matching. Four years as a startup CTO in between. Today I lead an engineering studio, and I keep my own research running alongside it.
- Ph.D., university in Korea
- CVPR · ICCV · TPAMI
- Zero to one, as a startup CTO
- Leads an engineering team
- 4× outstanding reviewer
What I work on
Since 2023 the work has arrived as several projects in parallel rather than one product, and my research has continued independently alongside it. Both halves are applied computer vision and applied AI, delivered as systems that hold up under real traffic rather than demos. Three domains take most of my time.
Smart transportation and parking
License plate detection and recognition, vehicle understanding, and the edge deployments that keep a gate moving when the camera is dirty, the light is wrong and the network is not cooperating.
Conversational AI
Assistants wired into the systems a business actually runs on, with authorization enforced at the object level so an agent can never answer with the wrong customer's data.
Research interests
Path
-
2012 – 2017
Ph.D., university in Korea
Information and communication engineering. Light field depth estimation, stereo matching and computational photography, published at CVPR, ICCV and TPAMI. Graduated with the Outstanding Researcher Award.
-
2017 – 2020
Faculty, private university in West Jakarta
Taught and advised in computer science while continuing to publish and supervise vision research.
-
2019 – 2023
Co-founder and CTO, AI verification startup
Took a product from nothing to production: the initial technology, the first models, and the engineering team that kept building after me. Four years of zero to one, which is the part of the work I am best at.
-
2023 – now
Running an engineering studio
I lead a team that takes on several projects at once rather than one product, from scoping through to the systems that end up carrying real load.
-
2023 – now
Independent researcher
Kept deliberately separate from the company. Still reviewing for the major vision conferences, and co-organizer of the Workshop on Computer Vision for Developing Countries across all three of its editions so far.
Publications
Google ScholarJournals
- 2022
- 2020
-
2019
6-DOF motion blur synthesis and performance evaluation of light field deblurring
Multimedia Tools and Applications
- 2018
-
2018
Cost aggregation benchmark for light field depth estimation
J. Visual Communication and Image Representation
-
2018
Deep self-guided cost aggregation for stereo matching
Pattern Recognition Letters
-
2016
Spatio-angular consistent editing framework for 4D light field images
Multimedia Tools and Applications
-
2015
Correcting geometric and photometric distortion of document images on a smartphone
Journal of Electronic Imaging
-
2014
Object-oriented framework for real-time image processing on GPU
Multimedia Tools and Applications
-
2014
Accurate and real-time depth video acquisition using Kinect-stereo camera fusion
Optical Engineering
Conferences
- 2024
- 2020
- 2018
- 2017
- 2016
- 2015
- 2014
- 2014
- 2012
Patents
- 2019
- 2019
- 2019
- 2016
Recognition and service
Awards
- Outstanding Reviewer, CVPR 2024top 2% of 9,872 reviewers
- Outstanding Reviewer, CVPR 2023top 3.5% of 6,625 reviewers
- Outstanding Reviewer, CVPR 2021top 20% of 5,250 reviewers
- Top 215 Reviewer, ECCV 2020top 7.6% of 2,830 reviewers
- Pioneer Winner, 2020global tournament for independent projects
- Outstanding Research Award, 2017Dean's choice of the best researcher, graduate school
- Best Student Paper Award, 2017Institute of Electronics and Information Engineers, Korea
- Best Paper Award, 201723rd Japan-Korea Workshop on Frontiers of Computer Vision
- Best Student Paper Award, 201628th Workshop on Image Processing and Image Understanding
Reviewing
| CVPR | 9 | 2018 – 2026, every year |
|---|---|---|
| ICCV | 4 | 2019, 2021, 2023, 2025 |
| ECCV | 3 | 2020, 2022, 2024 |
| ACCV | 3 | 2020, 2022, 2024 |
| WACV | 3 | 2021, 2022, 2024 |
| AAAI | 3 | 2020, 2021, 2022 |
| NeurIPS | 2 | 2022, 2024 |
| ICLR | 2 | 2022, 2024 |
Journals
Organizing
Co-organizer of the Workshop on Computer Vision for Developing Countries (CV4DC), every edition since it started.
- 1stCV4DC 2024with ACCV 2024
- 2ndCV4DC 2025with ICCV 2025
- 3rdCV4DC 2026with ACCV 2026
Contact
Open to research collaboration, technical advisory, and building things that have to work on the first day they meet real users.