no code implementations • 7 May 2024 • David Borts, Erich Liang, Tim Brödermann, Andrea Ramazzina, Stefanie Walz, Edoardo Palladin, Jipeng Sun, David Bruggemann, Christos Sakaridis, Luc van Gool, Mario Bijelic, Felix Heide
Neural fields have been broadly investigated as scene representations for the reproduction and novel generation of diverse outdoor scenes, including those autonomous vehicles and robots must handle.
1 code implementation • 27 Mar 2024 • Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segu, Siyuan Li, Luc van Gool, Fisher Yu
However, the remarkable accuracy of recent MMDE methods is confined to their training domains.
Ranked #2 on Monocular Depth Estimation on NYU-Depth V2 (using extra training data)
1 code implementation • 27 Jan 2024 • Diandian Guo, Deng-Ping Fan, Tongyu Lu, Christos Sakaridis, Luc van Gool
The estimation of implicit cross-frame correspondences and the high computational cost have long been major challenges in video semantic segmentation (VSS) for driving scenes.
no code implementations • 23 Jan 2024 • Tim Brödermann, David Bruggemann, Christos Sakaridis, Kevin Ta, Odysseas Liagouris, Jason Corkill, Luc van Gool
Achieving level-5 driving automation in autonomous vehicles necessitates a robust semantic visual perception system capable of parsing data from different sensors across diverse conditions.
1 code implementation • 7 Dec 2023 • Haofei Xu, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, Fisher Yu
We present Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view synthesis under multiple different baseline settings (small and large baselines, and different number of input views).
1 code implementation • NeurIPS 2023 • Zhejun Zhang, Alexander Liniger, Christos Sakaridis, Fisher Yu, Luc van Gool
The real-world deployment of an autonomous driving system requires its components to run on-board and in real-time, including the motion prediction module that predicts the future trajectories of surrounding traffic participants.
no code implementations • 8 Sep 2023 • Ozan Unal, Christos Sakaridis, Suman Saha, Fisher Yu, Luc van Gool
A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes.
1 code implementation • 27 May 2023 • Christos Sakaridis, David Bruggemann, Fisher Yu, Luc van Gool
Motivated by these findings, we propose to leverage stylization in performing feature-level adaptation by aligning the internal network features extracted by the encoder of the network from the original and the stylized view of each input image with a novel feature invariance loss.
no code implementations • 26 May 2023 • Jan Ackermann, Christos Sakaridis, Fisher Yu
We present a simple and practical framework for anomaly segmentation called Maskomaly.
1 code implementation • CVPR 2023 • Guolei Sun, Zhaochong An, Yun Liu, Ce Liu, Christos Sakaridis, Deng-Ping Fan, Luc van Gool
We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings.
1 code implementation • 21 Apr 2023 • Deng-Ping Fan, Ge-Peng Ji, Peng Xu, Ming-Ming Cheng, Christos Sakaridis, Luc van Gool
Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive objects exhibiting camouflage.
2 code implementations • CVPR 2023 • Luigi Piccinelli, Christos Sakaridis, Fisher Yu
Our method sets the new state of the art with significant improvements on NYU-Depth v2 and KITTI, outperforming all published methods on the official KITTI benchmark.
Ranked #3 on Surface Normals Estimation on NYU Depth v2
1 code implementation • 11 Apr 2023 • Xue-Jing Luo, Shuo Wang, Zongwei Wu, Christos Sakaridis, Yun Cheng, Deng-Ping Fan, Luc van Gool
Specifically, we leverage the latent diffusion model to synthesize salient objects in camouflaged scenes, while using the zero-shot image classification ability of the Contrastive Language-Image Pre-training (CLIP) model to prevent synthesis failures and ensure the synthesized object aligns with the input prompt.
1 code implementation • 25 Mar 2023 • Stamatis Alexandropoulos, Christos Sakaridis, Petros Maragos
Motivated by this prior, we design a novel two-head network, named Offset Vector Network (OVeNet), which generates both standard semantic predictions and a dense 2D offset vector field indicating the offset from each pixel to the respective seed pixel, which is used to compute an alternative, seed-based semantic prediction.
no code implementations • 21 Mar 2023 • Kamil Adamczewski, Christos Sakaridis, Vaishakh Patil, Luc van Gool
Lidar is a vital sensor for estimating the depth of a scene.
1 code implementation • ICCV 2023 • David Bruggemann, Christos Sakaridis, Tim Brödermann, Luc van Gool
We investigate normal-to-adverse condition model adaptation for semantic segmentation, whereby image-level correspondences are available in the target domain.
Ranked #1 on Source-Free Domain Adaptation on Cityscapes to ACDC
no code implementations • CVPR 2023 • Lei Sun, Christos Sakaridis, Jingyun Liang, Peng Sun, JieZhang Cao, Kai Zhang, Qi Jiang, Kaiwei Wang, Luc van Gool
The performance of video frame interpolation is inherently correlated with the ability to handle motion in the input scene.
1 code implementation • 27 Oct 2022 • Ge-Peng Ji, Mingcheng Zhuge, Dehong Gao, Deng-Ping Fan, Christos Sakaridis, Luc van Gool
We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation.
1 code implementation • 30 Sep 2022 • Anton Obukhov, Mikhail Usvyatsov, Christos Sakaridis, Konrad Schindler, Luc van Gool
Learning neural fields has been an active topic in deep learning research, focusing, among other issues, on finding more compact and easy-to-fit representations.
1 code implementation • 14 Jul 2022 • David Bruggemann, Christos Sakaridis, Prune Truong, Luc van Gool
Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images.
Ranked #1 on Semantic Segmentation on Dark Zurich
1 code implementation • 3 Jul 2022 • Kevin Ta, David Bruggemann, Tim Brödermann, Christos Sakaridis, Luc van Gool
As neuromorphic technology is maturing, its application to robotics and autonomous vehicle systems has become an area of active research.
1 code implementation • 30 Jun 2022 • Tim Broedermann, Christos Sakaridis, Dengxin Dai, Luc van Gool
Besides standard cameras, autonomous vehicles typically include multiple additional sensors, such as lidars and radars, which help acquire richer information for perceiving the content of the driving scene.
Ranked #1 on 2D Object Detection on Clear Weather
1 code implementation • CVPR 2022 • Vaishakh Patil, Christos Sakaridis, Alexander Liniger, Luc van Gool
We focus on the supervised setup, in which ground-truth depth is available only at training time.
Ranked #6 on Depth Estimation on NYU-Depth V2
1 code implementation • CVPR 2022 • Martin Hahner, Christos Sakaridis, Mario Bijelic, Felix Heide, Fisher Yu, Dengxin Dai, Luc van Gool
Due to the difficulty of collecting and annotating training data in this setting, we propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds.
Ranked #1 on 3D Object Detection on Heavy Snowfall
1 code implementation • 30 Nov 2021 • Lei Sun, Christos Sakaridis, Jingyun Liang, Qi Jiang, Kailun Yang, Peng Sun, Yaozu Ye, Kaiwei Wang, Luc van Gool
Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times.
Ranked #3 on Deblurring on GoPro (using extra training data)
1 code implementation • ICCV 2021 • Martin Hahner, Christos Sakaridis, Dengxin Dai, Luc van Gool
2) Through extensive experiments with several state-of-the-art detection approaches, we show that our fog simulation can be leveraged to significantly improve the performance for 3D object detection in the presence of fog.
Ranked #1 on 3D Object Detection on Dense Fog
no code implementations • ICCV 2021 • Christos Sakaridis, Dengxin Dai, Luc van Gool
To address this, we introduce ACDC, the Adverse Conditions Dataset with Correspondences for training and testing semantic segmentation methods on adverse visual conditions.
1 code implementation • 28 May 2020 • Christos Sakaridis, Dengxin Dai, Luc van Gool
Our central contributions are: 1) a curriculum framework to gradually adapt semantic segmentation models from day to night through progressively darker times of day, exploiting cross-time-of-day correspondences between daytime images from a reference map and dark images to guide the label inference in the dark domains; 2) a novel uncertainty-aware annotation and evaluation framework and metric for semantic segmentation, including image regions beyond human recognition capability in the evaluation in a principled fashion; 3) the Dark Zurich dataset, comprising 2416 unlabeled nighttime and 2920 unlabeled twilight images with correspondences to their daytime counterparts plus a set of 201 nighttime images with fine pixel-level annotations created with our protocol, which serves as a first benchmark for our novel evaluation.
Ranked #5 on Semantic Segmentation on Nighttime Driving
2 code implementations • 9 Oct 2019 • Martin Hahner, Dengxin Dai, Christos Sakaridis, Jan-Nico Zaech, Luc van Gool
This work addresses the problem of semantic scene understanding under foggy road conditions.
1 code implementation • ICCV 2019 • Christos Sakaridis, Dengxin Dai, Luc van Gool
Our central contributions are: 1) a curriculum framework to gradually adapt semantic segmentation models from day to night via labeled synthetic images and unlabeled real images, both for progressively darker times of day, which exploits cross-time-of-day correspondences for the real images to guide the inference of their labels; 2) a novel uncertainty-aware annotation and evaluation framework and metric for semantic segmentation, designed for adverse conditions and including image regions beyond human recognition capability in the evaluation in a principled fashion; 3) the Dark Zurich dataset, which comprises 2416 unlabeled nighttime and 2920 unlabeled twilight images with correspondences to their daytime counterparts plus a set of 151 nighttime images with fine pixel-level annotations created with our protocol, which serves as a first benchmark to perform our novel evaluation.
Ranked #7 on Semantic Segmentation on Nighttime Driving
1 code implementation • 5 Jan 2019 • Dengxin Dai, Christos Sakaridis, Simon Hecker, Luc van Gool
The method is based on the fact that the results of semantic segmentation in moderately adverse conditions (light fog) can be bootstrapped to solve the same problem in highly adverse conditions (dense fog).
Ranked #5 on Domain Adaptation on Cityscapes-to-FoggyDriving
no code implementations • ECCV 2018 • Christos Sakaridis, Dengxin Dai, Simon Hecker, Luc van Gool
In addition, we present three other main stand-alone contributions: 1) a novel method to add synthetic fog to real, clear-weather scenes using semantic input; 2) a new fog density estimator; 3) the Foggy Zurich dataset comprising $3808$ real foggy images, with pixel-level semantic annotations for $16$ images with dense fog.
8 code implementations • CVPR 2018 • Yuhua Chen, Wen Li, Christos Sakaridis, Dengxin Dai, Luc van Gool
The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
no code implementations • 25 Aug 2017 • Christos Sakaridis, Dengxin Dai, Luc van Gool
Due to the difficulty of collecting and annotating foggy images, we choose to generate synthetic fog on real images that depict clear-weather outdoor scenes, and then leverage these partially synthetic data for SFSU by employing state-of-the-art convolutional neural networks (CNN).
no code implementations • 24 Oct 2016 • Christos Sakaridis, Kimon Drakopoulos, Petros Maragos
Active contour models based on partial differential equations have proved successful in image segmentation, yet the study of their geometric formulation on arbitrary geometric graphs is still at an early stage.