Related papers: SIMBAR: Single Image-Based Scene Relighting For Ef…

Advancing research in fields such as Simultaneous Localization and Mapping (SLAM) and autonomous navigation critically depends on the availability of reliable and reproducible multimodal datasets. While several influential datasets have…

We are interested in understanding whether retrieval-based localization approaches are good enough in the context of self-driving vehicles. Towards this goal, we introduce Pit30M, a new image and LiDAR dataset with over 30 million frames,…

Multi-modal object detection in autonomous driving has achieved great breakthroughs due to the usage of fusing complementary information from different sensors. The calibration in fusion between sensors such as LiDAR and camera was always…

With the increasing global popularity of self-driving cars, there is an immediate need for challenging real-world datasets for benchmarking and training various computer vision tasks such as 3D object detection. Existing datasets either…

Moving object detection is a critical task for autonomous vehicles. As dynamic objects represent higher collision risk than static ones, our own ego-trajectories have to be planned attending to the future states of the moving elements of…

The validation of LiDAR-based perception of intelligent mobile systems operating in open-world applications remains a challenge due to the variability of real environmental conditions. Virtual simulations allow the generation of arbitrary…

We address the problem of 3D object detection from 2D monocular images in autonomous driving scenarios. We propose to lift the 2D images to 3D representations using learned neural networks and leverage existing networks working directly on…

We present a lighting-aware image editing pipeline that, given a portrait image and a text prompt, performs single image relighting. Our model modifies the lighting and color of both the foreground and background to align with the provided…

Illumination effects in images, specifically cast shadows and shading, have been shown to decrease the performance of deep neural networks on a large number of vision-based detection, recognition and segmentation tasks in urban driving…

Scene-aware Complementary Item Retrieval (CIR) is a challenging task which requires to generate a set of compatible items across domains. Due to the subjectivity, it is difficult to set up a rigorous standard for both data collection and…

For autonomous vehicles, an accurate calibration for LiDAR and camera is a prerequisite for multi-sensor perception systems. However, existing calibration techniques require either a complicated setting with various calibration targets, or…

The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating…

Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse…

Supervised networks address the task of low-light enhancement using paired images. However, collecting a wide variety of low-light/clean paired images is tedious as the scene needs to remain static during imaging. In this paper, we propose…

Deep-learning-based autonomous driving (AD) perception introduces a promising picture for safe and environment-friendly transportation. However, the over-reliance on real labeled data in LiDAR perception limits the scale of on-road…

Object detection in aerial images is an important task in environmental, economic, and infrastructure-related tasks. One of the most prominent applications is the detection of vehicles, for which deep learning approaches are increasingly…

Generative image models are increasingly being used for training data augmentation in vision tasks. In the context of automotive object detection, methods usually focus on producing augmented frames that look as realistic as possible, for…

Object detection and semantic segmentation with the 3D lidar point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation…

Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds…

Although LiDAR sensors are crucial for autonomous systems due to providing precise depth information, they struggle with capturing fine object details, especially at a distance, due to sparse and non-uniform data. Recent advances introduced…