News
- 10/2026 Released TAPVid-MV, a multi-view 3D point tracking benchmark, with Google DeepMind and UCL.
- 09/2026 Scaffold3D accepted to NeurIPS 2026.
- 02/2026 Invited to give a seminar at Sony CSL (Paris) on Multi-View 3D Point Tracking [recording].
- 10/2025 Presented Multi-View 3D Point Tracking as an ICCV 2025 Oral [video] [slides].
- 09/2025 Invited to give talks at Google XR Team and Meta Reality Labs on Multi-View 3D Point Tracking.
- 01/2024 Started PhD at ETH Zürich (VLG).
|
|
Selected Publications
|
|
TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views.
Skanda Koppula*, Frano Rajič*, Abdullah Faiz Ur Rahman, Yi Yang, Ignacio Rocco, Jeet Thakwani, Rishabh Kabra, Andrew Zisserman, Joao Carreira, Siyu Tang, Carl Doersch, Gabriel Brostow (* equal contribution).
arXiv preprint, 2026
project |
paper
|
|
Scaffold3D: SfM-Conditioned Pointmap Prediction for Multi-View 3D Reconstruction.
Frano Rajič, Yutong Chen, Haofei Xu, Zador Pataki, Marc Pollefeys, Siyu Tang.
Conference on Neural Information Processing Systems (NeurIPS), 2026
project |
paper
|
|
BulletTime: Decoupled Control of Time and Camera Pose for Video Generation.
Yiming Wang, Qihang Zhang, Shengqu Cai, Tong Wu, Jan Ackermann, Zhengfei Kuang, Yang Zheng, Frano Rajič, Siyu Tang, Gordon Wetzstein.
Conference on Computer Vision and Pattern Recognition (CVPR), 2026
project |
paper
|
|
Multi-View 3D Point Tracking.
Frano Rajič, Haofei Xu, Marko Mihajlovic, Siyuan Li, Irem Demir, Emircan Gündoğdu, Lei Ke, Sergey Prokudin, Marc Pollefeys, Siyu Tang.
International Conference on Computer Vision (ICCV), 2025 (Oral, top 0.5%)
project |
code |
video |
slides
|
|
SAM-PT: Segment Anything Meets Point Tracking.
Frano Rajič, Lei Ke, Yu-Wing Tai, Chi-Keung Tang, Martin Danelljan, Fisher Yu.
Winter Conference on Applications of Computer Vision (WACV), 2025 (1K+ stars)
code |
paper |
hf daily paper
|
|
Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations.
Ahmad Rahimi, Po-Chien Luan, Yuejiang Liu, Frano Rajič, Alexandre Alahi.
Conference on Computer Vision and Pattern Recognition (CVPR), 2025
paper |
code
|
|
Language Model Decoding as Likelihood-Utility Alignment.
Martin Josifoski, Maxime Peyrard, Frano Rajič, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kıcıman, Boi Faltings, Robert West.
Findings of the Conference of the European Chapter of the Association for Computational Linguistics (EACL Findings), 2023
paper |
code
|
|
Robustness of Embodied Point Navigation Agents.
Frano Rajič.
European Conference on Computer Vision Workshops (ECCVW), 2022
project page |
paper
|
Invited Talks
- 31.08.2026 EFCL–Huawei Workshop in Zürich: 4D Dynamic Tracking and Reconstruction.
- 18.02.2026 Sony CSL Etincelle Seminar (hosted by David Colliaux) on Multi-View 3D Point Tracking. [recording]
- 21.10.2025 ICCV 2025 Oral (Honolulu, US): Multi-View 3D Point Tracking. [recording] [slides]
- 22.09.2025 Google XR Team talk (hosted by Johanna Wald) on Multi-View 3D Point Tracking.
- 17.09.2025 Meta Reality Labs talk in Zürich (hosted by Christian Richardt) on Multi-View 3D Point Tracking.
|
Selected Honors & Awards
- EDIC PhD Fellowship offer, EPFL, Top 5% of applicants (2023).
- MSc in Data Science, EPFL, Rank 2/84, GPA 5.85/6 (2023).
- Dean's Recognition of Excellence "Josip Lončar", UniZG-FER, Rank 1/475 (2021).
- Student Award for Digital Innovation, Hanza Media, sponsored by Google, Rank 2/60 (2020).
- National Matriculation Exam, Croatia, Rank 1/11,644 in Mathematics and 1/2,299 in Informatics (2017).
|
Mentored Students
- MSc Theses: Hongyi Liu (2025), Ramanathan Rajaraman (co-supervised, 2025; next: PhD at NUS).
- MSc Semester Projects: Seung Ju Paek (2026), Dario Monopoli (2026), Pia Rosebelle Musni dela Paz (2026), Roman Zberg (2026), Matteo Lombard (2026), Emircan Gündoğdu (2024; co-author of Multi-View 3D Point Tracking), Irem Demir (2024; co-author of Multi-View 3D Point Tracking).
- BSc Theses: Mavin Weihrauch (2026), Romy Viehweg (co-supervised, 2026), Dante Boeri (co-supervised, 2026), Fabio Di Meo (2026; next: Research Assistant at ETH Zürich), Raman Besenfelder (2025; next: MSc at ETH Zürich).
|
Teaching
- Teaching Assistant, Computer Vision, ETH Zürich, Fall 2026.
- Teaching Assistant, Digital Humans, ETH Zürich, Spring 2026.
- Teaching Assistant, Computer Vision, ETH Zürich, Fall 2025.
- Teaching Assistant, Data Structures and Algorithms, ETH Zürich, Spring 2025.
- Teaching Assistant, Computer Science II, ETH Zürich, Fall 2024.
- Teaching Assistant, Digital Humans, ETH Zürich, Spring 2024.
- Educator, Youth Research Centre (ICM), Zagreb, Croatia, December 2017 – April 2020.
- Teaching Assistant, Advanced Use of Linux, UniZG-FER, Spring 2019.
- Teaching Assistant, Basic Use of Linux, UniZG-FER, Fall 2018.
- Teaching Assistant, Digital Logic, UniZG-FER, Fall 2017.
- Co-founder and Educator, Acervatio, Gymnasium Metković, Croatia, 2016 – 2018.
|
|
