F. Güney @fguney.bsky.social · 31/03/2026Sadra is on 🔥 this week 🧿 we present FlowIt: Global Matching for Optical Flow with Confidence-Guided Refinement arxiv.org/abs/2603.28759 as someone who published her first flow paper 10 years ago, I cannot believe how good these results are: 2112
F. Güney @fguney.bsky.social · 31/03/2026Sadra released the code for WarpRF 🚀 a training-free uncertainty quantification framework for radiance fields based on multi-view consistency, without training or any changes to the model. 153
F. Güney @fguney.bsky.social · 10/12/2025I have a feeling you’d enjoy this comment as much as I did 😂 000
F. Güney @fguney.bsky.social · 24/11/2025Fatih is presenting our work Mapping like a Skeptic 🔎 tomorrow at #BMVC2025! paper: arxiv.org/abs/2508.21689 code: github.com/Fatih-Erdoga... 060
F. Güney @fguney.bsky.social · 21/11/2025what a nice way to end an amazing 2-day workshop in Grenoble 😊 040
F. Güney @fguney.bsky.social · 03/02/2025We introduce a flexible memory extension mechanism, allowing users to adapt based on FPS, frame count, and other data characteristics. Our model is fast and lightweight, requiring minimal GPU memory. (6/7) 100
F. Güney @fguney.bsky.social · 03/02/2025Even without bidirectional information flow (unlike offline models), our approach achieves state-of-the-art results among comparable online and offline tracking models across multiple datasets. (5/7) 100
F. Güney @fguney.bsky.social · 03/02/2025Unlike traditional methods relying on full temporal modeling, our model operates causally—processing frames without future information. We introduce two memory modules: (i) Spatial Memory, addressing feature drift; (ii) Context Memory, storing full tracking history. (4/7) 100
F. Güney @fguney.bsky.social · 03/02/2025We simply process points as queries in a transformer decoder. Instead of regressing coordinates (as in dominant methods), we treat tracking as a classification problem, selecting the most likely patch per query and refining with local offsets. (3/7) 100
F. Güney @fguney.bsky.social · 03/02/2025Unlike prior work focused on offline point tracking, we target online tracking on a frame-by-frame basis, making it ideal for real-time, streaming scenarios. At the core of our approach is a simple yet effective transformer-based model. (2/7) 110
F. Güney @fguney.bsky.social · 06/01/2025Efe, one of our interns last summer, implemented the ROACH expert on NAVSIM and apparently shared the code: github.com/efemantarci/... there is no documentation but it should be fairly easy to use in case you need an RL expert reaching the performance of TransFuser on NAVSIM. 030
F. Güney @fguney.bsky.social · 07/12/2024Mısra will present Odd-One-Out next week at #ACCV2024, check out her talk in Oral Session 5 on day 3 (December 12 at 9:00). kuis-ai.github.io/O1O/ unfortunately, I won't be there -teaching is falling apart due to too much traveling-, but I'm looking forward to visiting Vietnam in the future 🙂 080
F. Güney @fguney.bsky.social · 27/11/2024vow Sadra won the best poster award at #BMVC 🥳 I should have paid for the gala dinner this time 😂 8370
F. Güney @fguney.bsky.social · 26/11/2024in a country where it rains and snows all the time, there was an hour of sunshine today during our visit to #GlasgowNecropolis. one hour Scotland, I needed one hour of your default gloomy weather with rain and darkness. result: cheery photos in a gothic cemetery 🙄 170
F. Güney @fguney.bsky.social · 24/11/2024Sadra and I will be in Glasgow for the next few days, presenting our work with Matteo and Fabio at #BMVC tomorrow. I will be visiting some friends in Edinburgh afterwards and give a talk on Friday, looking forward to it all! last time I visited Scotland was in August, I cannot imagine late Nov 😅 1231
