Tolga Birdal

News

• [03.06.19] I moved to Stanford. For all recent news visit here. For inquiries about research stays/supervision, please send me an e-mail.
• [25.02.19] I have 3 papers accepted at CVPR 2019, 1 of which is oral.
• [13.02.19] Our paper "Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits" got accepted for T-PAMI. Check the pre-print here (author's copy below).
• [19.12.18] I defended! My thesis is online at mediaTUM.
• [06.09.18] 1 paper accepted at NIPS 2018.
• [21.07.18] 1 paper accepted at 3DV 2018.
• [04.07.18] 1 paper accepted at ECCV 2018.
• [21.02.18] I will be presenting my work at CVPR Doctoral Consortium on 20.06.2018.
• [19.02.18] 2 papers accepted for publication at CVPR 2018!
• [29.10.17] Our paper on 3D camera pose filtering received The Best Paper Award at ICCV 2017 Workshop on Multiview Relationships in 3D Data. Find out more here.
• [15.07.17] Our paper on 3D reconstruction using CAD proxies is accepted at ICCV 2017. Find out more here.
• [12.07.17] My second opinion & analysis piece regarding 3D vision published at IMV Europe. Available online here.
• [13.06.17] I am proudly co-organizing ICCV 2017 Workshop on Multiview Relationships in 3D Data. The workshop hosts amazing set of speakers with noteworthy awards! Make sure to check it out.
• [12.09.16] Imaging and Machine Vision Europe, the famous machine vision magazine, publishes an interview with myself, regarding EMVA award.
• [09.09.16] Our paper "X-Tag: A Fiducial Tag for Flexible and Accurate Bundle Adjustment" got accepted to 3DV 2016.
• [11.06.16] I have received the prestigious EMVA Young Professional Award 2016, for a part of my PhD work.
• [12.08.15] Our paper "Point Pair Features Based Object Detection and Pose Estimation Revisited" got accepted as an oral presentation at 3DV 2015.

Brief Bio

Tolga Birdal received his PhD from the Computer Vision Group at the Chair for Computer Aided Medical Procedures, TUM sponsored by Siemens AG. He completed his Bachelors as an Electronics Engineer at the Sabanci University in 2008. In his subsequent postgraduate programme, he studied Computational Science and Engineering at Technical University of Munich. In continuation to his Master's thesis on “3D Deformable Surface Recovery Using RGBD Cameras”, he now focuses his research and development on large object detection, pose estimation and reconstruction. Recently, he is awarded Ernst von Siemens Scholarship and EMVA Young Professional Award 2016 for his PhD work. He has several publications at the well respected venues such as NIPS, CVPR, ICCV, ECCV, IROS, ICASSP and 3DV. Aside from his academic life, Tolga is a natural Entrepreneur. He has founded multiple companies including Befunky, a widely used web based image processing platform. He is a Jazz lover, enjoys drumming and appreciates the delicate taste of whisky.

Research Topics

I am currently involved in conducting research in the following research areas.

• 3D reconstruction and shape recovery in point clouds.
• Real-time 3D object detection and tracking.
• Robust, real-time point cloud matching
• 3D object detection in depth data.
• Multiple view geometry and camera calibration.
• Geometric object modeling.
• Machine learning and pattern recognition

Active research projects

Learning, Understanding and Reconstructing Point Clouds Point clouds offer a unified representation for 3D data. Whether the sensor is a laser scanner, lidar or a depth camera, the acquired information can be stored in form an unstructured point cloud. This makes such representation ubiquitous. In this project, we aim to adapt state-of-the-art learning algorithms to efficiently handle point cloud data in order to find objects, detect structures, perform segmentation and 3d reconstruction.

Education

• 2008-2011 - Computational Science and Engineering / Technical University of Munich, Germany
• 2004-2008 - Electronics Engineering / Sabanci University, Istanbul, Turkiye
• 2000-2004 - Robert College, Istanbul, Turkiye

Teaching Assistance Lecture: Tracking and Detection in Computer Vision (WS 17/18) Seminar: Recent Trends in 3D Computer Vision (WS 16/17) Lecture: Tracking and Detection in Computer Vision (WS 16/17) Seminar: Recent Trends in 3D Computer Vision (WS 15/16) Lecture: Tracking and Detection in Computer Vision (WS 15/16) Lecture: Tracking and Detection in Computer Vision (WS 14/15)

Publications

2020
	M. Bui, T. Birdal, H. Deng, S. Albarqouni, L. Guibas, S. Ilic, N. Navab 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference Proceedings of European Conference on Computer Vision, 2020, Glasgow (bib)
2019
	F. Manhardt, D. Arroyo, C. Rupprecht, B. Busam, T. Birdal, N. Navab, F. Tombari Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data International Conference on Computer Vision (ICCV), Seoul, Korea, October 2019 (bib)
	Y. Zhao, T. Birdal, H. Deng, F. Tombari 3D Point-Capsule Networks IEEE Computer Vision and Pattern Recognition (CVPR), Long Beach, United States, June 2019 (bib)
	T. Birdal, U. Simsekli Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope IEEE Computer Vision and Pattern Recognition (CVPR), Long Beach, United States, June 2019 [oral] (bib)
	H. Deng, T. Birdal, S. Ilic 3D Local Features for Direct Pairwise Registration IEEE Computer Vision and Pattern Recognition (CVPR), Long Beach, United States, June 2019 (bib)
	T. Birdal, B. Busam, N. Navab, S. Ilic, P. Sturm Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019 (bib)
2018
	T. Birdal, U. Simsekli, M. O. Eken, S. Ilic Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC Advances in Neural Information Processing Systems Conference (NIPS), Montréal, Quebec, Canada 2018 (poster) (supplementary) (bib)
	H. Deng, T. Birdal, S. Ilic PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors European Conference On Computer Vision (ECCV), Munich, Germany, September 2018 (bib)
	A. Haarbach, T. Birdal, S. Ilic Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory Estimation International Conference on 3D Vision (3DV), Verona, Italy, September 2018 [spotlight] (bib)
	T. Birdal, B. Busam, N. Navab, S. Ilic, P. Sturm A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds IEEE Computer Vision and Pattern Recognition (CVPR), Salt Lake City, United States, June 2018 (bib)
	H. Deng, T. Birdal, S. Ilic PPFNet: Global Context Aware Local Features for Robust 3D Point Matching IEEE Computer Vision and Pattern Recognition (CVPR), Salt Lake City, United States, June 2018 [spotlight] (bib)
2017
	B. Busam, T. Birdal, N. Navab Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternions International Conference on Computer Vision Workshop (ICCVW) on Multiview Relationships in 3D Data, Venice, Italy, October 2017 [oral]. (bib)
	T. Birdal, S. Ilic CAD Priors for Accurate and Flexible Instance Reconstruction International Conference on Computer Vision (ICCV), Venice, Italy, October 2017 (bib)
	T. Birdal, S. Ilic A Point Sampling Algorithm for 3D Matching of Irregular Geometries IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 2017 (bib)
2016
	T. Birdal, I. Dobryden, S. Ilic X-Tag: A Fiducial Tag for Flexible and Accurate Bundle Adjustment International Conference on 3DVision (3DV), Stanford University, California, USA, October 2016 (bib)
	T. Birdal, E. Bala, T. Eren, S. Ilic Online Inspection of 3D Parts via a Locally Overlapping Camera Network IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, March 2016 (bib)
2015
	T. Birdal, S. Ilic Point Pair Features Based Object Detection and Pose Estimation Revisited IEEE Computer Society Conference on 3D Vision (3DV), Lyon, France, October 2015 [oral] (poster) (bib)
	U. Simsekli, T. Birdal A Unified Probabilistic Framework for Robust Decoding of Linear Barcodes IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia, April 2015 (bib)
2012
	T. Birdal, D. Mateus, S. Ilic Towards A Complete Framework For Deformable Surface Recovery Using RGBD Cameras IEEE IROS'12 Workshop on Color-Depth Fusion in Robotics, Vila Moura, Portugal, October 2012 (bib)