Search
Results
-
Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding
(2018)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2018 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIIIThis work addresses the problem of semantic scene understanding under dense fog. Although considerable progress has been made in semantic scene understanding, it is mainly related to clear-weather scenes. Extending recognition methods to adverse weather conditions such as fog is crucial for outdoor applications. In this paper, we propose a novel method, named Curriculum Model Adaptation (CMAda), which gradually adapts a semantic segmentation ...Conference Paper -
ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)Level 5 autonomy for self-driving cars requires a robust visual perception system that can parse input images under any visual condition. However, existing semantic segmentation datasets are either dominated by images captured under normal conditions or are small in scale. To address this, we introduce ACDC, the Adverse Conditions Dataset with Correspondences for training and testing semantic segmentation methods on adverse visual conditions. ...Conference Paper -
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)This work addresses the challenging task of LiDAR-based 3D object detection in foggy weather. Collecting and annotating data in such a scenario is very time, labor and cost intensive. In this paper, we tackle this problem by simulating physically accurate fog into clear-weather scenes, so that the abundant existing real datasets captured in clear weather can be repurposed for our task. Our contributions are twofold: 1) We develop a ...Conference Paper -
LiDAR Snowfall Simulation for Robust 3D Object Detection
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)3D object detection is a central task for applications such as autonomous driving, in which the system needs to localize and classify surrounding traffic agents, even in the presence of adverse weather. In this paper, we address the problem of LiDAR-based 3D object detection under snowfall. Due to the difficulty of collecting and annotating training data in this setting, we propose a physically based method to simulate the effect of ...Conference Paper -
Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion
(2023)Proceedings of Machine Learning Research ~ Proceedings of the 6th Conference on Robot LearningLidar is a vital sensor for estimating the depth of a scene. Typical spinning lidars emit pulses arranged in several horizontal lines and the monetary cost of the sensor increases with the number of these lines. In this work, we present the new problem of optimizing the positioning of lidar lines to find the most effective configuration for the depth completion task. We propose a solution to reduce the number of lines while retaining the ...Conference Paper -
P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Monocular depth estimation is vital for scene understanding and downstream tasks. We focus on the supervised setup, in which ground-truth depth is available only at training time. Based on knowledge about the high regularity of real 3D scenes, we propose a method that learns to selectively leverage information from coplanar pixels to improve the predicted depth. In particular, we introduce a piecewise planarity prior which states that for ...Conference Paper -
Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation
(2019)2019 IEEE/CVF International Conference on Computer Vision (ICCV)Most progress in semantic segmentation reports on daytime images taken under favorable illumination conditions. We instead address the problem of semantic segmentation of nighttime images and improve the state-of-the-art, by adapting daytime models to nighttime without using nighttime annotations. Moreover, we design a new evaluation framework to address the substantial uncertainty of semantics in nighttime images. Our central contributions ...Conference Paper -
Semantic Understanding of Foggy Scenes with Purely Synthetic Data
(2019)2019 IEEE Intelligent Transportation Systems Conference (ITSC)This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Extending semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, ...Conference Paper -
Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding
(2023)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. Existing agent-centric methods have demonstrated outstanding performance on public benchmarks. However, they suffer from high computational overhead and poor scalability as the number of agents to be predicted ...Conference Paper -
Domain Adaptive Faster R-CNN for Object Detection in the Wild
(2018)2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionConference Paper