Introduction

I am currently employed as a Computer Vision and Machine Learning Research Scientist in the Computer Vision Lab at Huawei, Zurich. I work on developing memory- and computationally-efficient image restoration models for the next-generation smartphones and cloud services.
Prior to joining Huawei, I received a PhD from ETH Zurich under the supervision of Prof. Dr. Luc Van Gool, where I explored data-efficient LiDAR semantic segmentation. My research spanned various approaches, including but not limited to weakly-supervised, semi-supervised training and active learning. In the later stages of my PhD, I contributed to the TRACE-Zurich project, shifting my focus towards integrating 3D vision with natural language, particularly in dense 3D visual grounding.

News

2024-09   My student’s work S4A is accepted to NeurIPS 2024 as Spotlight!
2024-05   DiAL receives Best Paper Award - Honorable Mention from IEEE RA-L 2023!
2023-10   ConcreteNet wins the ICCV 2023 Object Localization Challenge!
2022-03   ScribbleKITTI is accepted to CVPR 2022 as an ORAL paper!
2021-10   Our follow-up work in MedIA 2021 receives the Runner-up Best Paper Award!
2019-10   Our paper in MICCAI 2019 is accepted as an ORAL!

Selected Publications

Thumbnail
Scribble-Supervised LiDAR Semantic Segmentation
Ozan Unal, Dengxin Dai, Luc Van Gool

Conference on Computer Vision and Pattern Recognition (CVPR) 2022, ORAL

Thumbnail
Discwise Active Learning for LiDAR Semantic Segmentation
Ozan Unal, Dengxin Dai, Ali Tamer Unal, Luc Van Gool

IEEE Robotics and Automation Letters 2023, Best Paper Award - Honorable Mention

Thumbnail
Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
Ozan Unal, Christos Sakaridis, Suman Saha, Luc Van Gool

European Conference on Computer Vision (ECCV) 2024

Thumbnail
Bayesian Self-Training for Semi-Supervised 3D Segmentation
Ozan Unal, Christos Sakaridis, Luc Van Gool

European Conference on Computer Vision (ECCV) 2024