Ayça Takmaz

I am a PhD student at ETH Zurich working on 3D scene understanding for augmented reality and robotics applications, supervised by Prof. Bob Sumner and co-supervised by Prof. Siyu Tang. I closely collaborate with Francis Engelmann. During my PhD, I also had the opportunity to intern at NVIDIA in Santa Clara with Aljosa Osep and Laura Leal-Taixe, and at Google in Zurich with Johanna Wald and Federico Tombari.

Prior to that, I finished my Master's at ETH Zurich with a focus on computer vision and machine learning. During this time, I spent time at the Computer Vision Lab (CVL) with Prof. Luc Van Gool, and the Computer Vision and Graphics (CVG) Group with Prof. Marc Pollefeys for my research projects in collaboration with Danda Pani Paudel and Martin R. Oswald.

News

Apr 2025 - Towards Learning to Complete Anything in Lidar (CAL) from my internship at NVIDIA is available as a pre-print!
Jan 2025 - Search3D from my internship at Google is accepted at IEEE Robotics and Automation Letters, RA-L!
Dec 2024 - 4^th iteration of our Open-Vocabulary 3D Scene Understanding Workshop will be held at CVPR'25 in Nashville!
July 2024 - I joined NVIDIA as a research intern - I will be based in Santa Clara for the upcoming months!
July 2024 - I attended ICVSS 2024 at Sicily, Italy - and our poster for OpenMask3D won 3rd place for the Best Poster Awards!
July 2024 - Our work Segment3D was accepted at ECCV 2024!
Apr 2024 - I started my internship at Google Zurich as a student researcher!
Apr 2024 - SceneFun3D is selected as an Oral Presentation for CVPR 2024!
Apr 2024 - 3^rd iteration of our Open-Vocabulary 3D Scene Understanding Workshop OpenSUN3D will be held at ECCV'24 in Milan!
Feb 2024 - Our work SceneFun3D was accepted at CVPR 2024!

Dec 2023 - 2^nd iteration of our Open-Vocabulary 3D Scene Understanding Workshop OpenSUN3D will be held in conjunction with CVPR'24 in Seattle!
Dec 2023 - Our NeurIPS 2023 paper on open vocabulary 3D instance segmentation OpenMask3D was featured in the Computer Vision News!
Sep 2023 - Our work OpenMask3D was accepted at NeurIPS 2023!
Jul 2023 - Our work Human3D was accepted at ICCV 2023!
Mar 2023 - Our workshop OpenSUN3D on Open-Vocabulary 3D Scene Understanding will be held in conjunction with ICCV 2023 in Paris!
Dec 2021 - I am starting my PhD in computer vision and augmented reality, under the supervision of Prof. Bob Sumner in the Department of Computer Science (D-INFK) at ETH Zurich!
Oct 2021 - Our work Unsupervised Monocular Reconstruction of Non-Rigid Scenes was accepted at 3DV 2021!

Publications

	Towards Learning to Complete Anything in Lidar Ayça Takmaz, Cristiano Saltori, Neehar Peri, Tim Meinhardt, Riccardo de Lutio, Laura Leal-Taixé, Aljosa Osep *Pre-print, 2025* project page / paper
	Search3D: Hierarchical Open-Vocabulary 3D Segmentation Ayça Takmaz, Alexandros Delitzas, Robert W. Sumner, Francis Engelmann, Johanna Wald, Federico Tombari *IEEE Robotics and Automation Letters (RA-L) 2025* project page / paper
	Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels Rui Huang, Songyou Peng, Ayça Takmaz, Federico Tombari, Marc Pollefeys, Shiji Song, Gao Huang, Francis Engelmann *European Conference on Computer Vision (ECCV) 2024* project page / paper
	SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes Alexandros Delitzas, Ayça Takmaz, Federico Tombari, Robert Sumner, Marc Pollefeys, Francis Engelmann *Computer Vision and Pattern Recognition (CVPR) 2024* *(Oral)* project page /paper
	OpenMask3D: Open-Vocabulary 3D Instance Segmentation Ayça Takmaz, Elisabetta Fedele, Robert W. Sumner, Marc Pollefeys, Federico Tombari, Francis Engelmann *Conference on Neural Information Processing Systems (NeurIPS) 2023* project page / paper
	3D Segmentation of Humans in Point Clouds with Synthetic Data Ayça Takmaz, Jonas Schult, Irem Kaftan, Mertcan Akcay, Bastian Leibe, Robert Sumner, Francis Engelmann, Siyu Tang *International Conference on Computer Vision (ICCV) 2023* project page / paper
	Unsupervised Monocular Reconstruction of Non-Rigid Scenes Ayça Takmaz, Danda Pani Paudel, Thomas Probst, Ajad Chhatkuli, Martin R. Oswald, Luc Van Gool *International Conference on 3D Vision (3DV) 2021* project page / paper
	Learning Feature Representations for Look-Alike Images Ayça Takmaz, Thomas Probst, Danda Pani Paudel, Luc Van Gool *Computer Vision and Pattern Recognition (CVPR) Workshops 2019* paper