no code implementations • 18 Sep 2023 • Ege Onat Özsüer, Barış Akgün, Fatma Güney
Reinforcement Learning (RL) has the potential to surpass human performance in driving without needing any expert supervision.
no code implementations • 8 Sep 2023 • Youssef Shoeb, Robin Chan, Gesina Schwalbe, Azarm Nowzard, Fatma Güney, Hanno Gottschalk
In this work, we extend beyond identifying OoD road obstacles in video streams and offer a comprehensive approach to extract sequences of OoD road obstacles using text queries, thereby proposing a way of curating a collection of OoD data for subsequent analysis.
no code implementations • ICCV 2023 • Görkay Aydemir, Adil Kaan Akan, Fatma Güney
To address this challenge, we propose ADAPT, a novel approach for jointly predicting the trajectories of all agents in the scene with dynamic weight learning.
no code implementations • ICCV 2023 • Sadra Safadoust, Fatma Güney
We achieve state-of-the-art results in unsupervised multi-object segmentation on synthetic and real-world datasets by modeling the scene structure and object motion.
no code implementations • 5 Jan 2023 • Sadra Safadoust, Fatma Güney
We perform experiments on the KITTI driving dataset and show that the planar parallax approach, which only needs to predict camera translation, can be a metrically accurate alternative to the current methods that rely on estimating 6DoF camera motion.
1 code implementation • ICCV 2023 • Nazir Nayal, Mısra Yavuz, João F. Henriques, Fatma Güney
Our extensive experiments show that mask classification improves the performance of the existing outlier detection methods, and the best results are achieved with the proposed RbA.
Ranked #1 on Anomaly Detection on Road Anomaly (using extra training data)
1 code implementation • 30 Oct 2022 • Çağan Selim Çoban, Oğuzhan Keskin, Jordi Pont-Tuset, Fatma Güney
In Video Instance Segmentation (VIS), current approaches either focus on the quality of the results, by taking the whole video as input and processing it offline; or on speed, by handling it frame by frame at the cost of competitive performance.
1 code implementation • 1 Jul 2022 • Görkay Aydemir, Adil Kaan Akan, Fatma Güney
We complement our representation with two types of memory modules; one focusing on the agent of interest and the other on the entire scene.
Ranked #51 on Motion Forecasting on Argoverse CVPR 2020
no code implementations • 25 Mar 2022 • Adil Kaan Akan, Fatma Güney
Our model learns temporal dynamics in a latent space through stochastic residual updates at each time step.
no code implementations • 20 Mar 2022 • Adil Kaan Akan, Sadra Safadoust, Fatma Güney
The existing methods fail to fully capture the dynamics of the structured world by only focusing on changes in pixels.
no code implementations • 8 Nov 2021 • Farzin Negahbani, Onur Berk Töre, Fatma Güney, Baris Akgun
Most autonomous vehicles are equipped with LiDAR sensors and stereo cameras.
no code implementations • 21 Oct 2021 • Sadra Safadoust, Fatma Güney
Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them.
1 code implementation • ICCV 2021 • Adil Kaan Akan, Erkut Erdem, Aykut Erdem, Fatma Güney
Motion is an important cue for video prediction and often utilized by separating video content into static and dynamic components.
Ranked #1 on Video Prediction on Cityscapes 128x128 (PSNR metric)
no code implementations • 18 Apr 2017 • Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes.