143 citations · 160 across the 16 of their papers we have counts for
20 papers
Progressive Risk Estimation for Accident Anticipation
Samet Hicsonmez, Eray Çakar, Nermin Samet +1
Accident anticipation aims to recognize anomalous driving cues before a crash while avoiding false alarms during normal driving. Existing approaches typically formulate this task a…
Real-World Point Tracking with Verifier-Guided Pseudo-Labeling
Görkay Aydemir, Fatma Güney, Weidi Xie
Models for long-term point tracking are typically trained on large synthetic datasets. The performance of these models degrades in real-world videos due to different characteristic…
Track-On2: Enhancing Online Point Tracking with Memory
Görkay Aydemir, Weidi Xie, Fatma Güney
In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across video frames under significant appearance changes, mot…
Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
Fatih Erdoğan, Merve Rabia Barın, Fatma Güney
Constructing high-definition (HD) maps from sensory input requires accurately mapping the road elements in image space to the Bird's Eye View (BEV) space. The precision of this map…
WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields
Sadra Safadoust, Fabio Tosi, Fatma Güney +1
We introduce WarpRF, a training-free general-purpose framework for quantifying the uncertainty of radiance fields. Built upon the assumption that photometric and geometric consiste…
ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models
Shadi Hamdan, Chonghao Sima, Zetong Yang +2
How can we benefit from large models without sacrificing inference speed, a common dilemma in self-driving systems? A prevalent solution is a dual-system architecture, employing a…
Track-On: Transformer-based Online Point Tracking with Memory
Görkay Aydemir, Xiongyi Cai, Weidi Xie +1
In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appeara…
Robust Bird's Eye View Segmentation by Adapting DINOv2
Merve Rabia Barın, Görkay Aydemir, Fatma Güney
Extracting a Bird's Eye View (BEV) representation from multiple camera images offers a cost-effective, scalable alternative to LIDAR-based solutions in autonomous driving. However,…
Self-supervised Object-Centric Learning for Videos
Görkay Aydemir, Weidi Xie, Fatma Güney
Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such…
Privileged to Predicted: Towards Sensorimotor Reinforcement Learning for Urban Driving
Ege Onat Özsüer, Barış Akgün, Fatma Güney
Reinforcement Learning (RL) has the potential to surpass human performance in driving without needing any expert supervision. Despite its promise, the state-of-the-art in sensorimo…
ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation
Görkay Aydemir, Adil Kaan Akan, Fatma Güney
Forecasting future trajectories of agents in complex traffic scenes requires reliable and efficient predictions for all agents in the scene. However, existing methods for trajector…
Multi-Object Discovery by Low-Dimensional Object Motion
Sadra Safadoust, Fatma Güney
Recent work in unsupervised multi-object segmentation shows impressive results by predicting motion from a single image despite the inherent ambiguity in predicting motion without…
DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax
Sadra Safadoust, Fatma Güney
Current self-supervised monocular depth estimation methods are mostly based on estimating a rigid-body motion representing camera motion. These methods suffer from the well-known s…
Two-Level Temporal Relation Model for Online Video Instance Segmentation
Çağan Selim Çoban, Oğuzhan Keskin, Jordi Pont-Tuset +1
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 h…
Trajectory Forecasting on Temporal Graphs
Görkay Aydemir, Adil Kaan Akan, Fatma Güney
Predicting future locations of agents in the scene is an important problem in self-driving. In recent years, there has been a significant progress in representing the scene and the…
StretchBEV: Stretching Future Instance Prediction Spatially and Temporally
Adil Kaan Akan, Fatma Güney
In self-driving, predicting future in terms of location and motion of all the agents around the vehicle is a crucial requirement for planning. Recently, a new joint formulation of…
Frustum Fusion: Pseudo-LiDAR and LiDAR Fusion for 3D Detection
Farzin Negahbani, Onur Berk Töre, Fatma Güney +1
Most autonomous vehicles are equipped with LiDAR sensors and stereo cameras. The former is very accurate but generates sparse data, whereas the latter is dense, has rich texture an…
Self-Supervised Monocular Scene Decomposition and Depth Estimation
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. We propose Mono…
On the Integration of Optical Flow and Action Recognition
Laura Sevilla-Lara, Yiyi Liao, Fatma Guney +3
Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and inv…
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Joel Janai, Fatma Güney, Aseem Behl +1
Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it becomes…