相关论文: G2D: from GTA to Data

We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras. Key to our approach is the use of self-supervised neural networks specific to the scene to compose…

We propose GGS, a Generalizable Gaussian Splatting method for Autonomous Driving which can achieve realistic rendering under large viewpoint changes. Previous generalizable 3D gaussian splatting methods are limited to rendering novel views…

3D Gaussian Splatting (3DGS) is an emerging media representation that reconstructs real-world 3D scenes in high fidelity, enabling 6-degrees-of-freedom (6-DoF) navigation in virtual reality (VR). However, developing and evaluating…

Vast and high-quality data are essential for end-to-end autonomous driving systems. However, current driving data is mainly collected by vehicles, which is expensive and inefficient. A potential solution lies in synthesizing data from…

Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into a bird's eye view, also known as plan…

In recent years, geospatial big data (GBD) has obtained attention across various disciplines, categorized into big earth observation data and big human behavior data. Identifying geospatial patterns from GBD has been a vital research focus…

Digital Twins (DTs) are virtual representations of physical objects or processes that can collect information from the real environment to represent, validate, and replicate the physical twin's present and future behavior. The DTs are…

Scalable sensor simulation is an important yet challenging open problem for safety-critical domains such as self-driving. Current works in image simulation either fail to be photorealistic or do not model the 3D environment and the dynamic…

3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a…

We introduce the novel task of Pano2Vid $-$ automatic cinematography in panoramic 360$^{\circ}$ videos. Given a 360$^{\circ}$ video, the goal is to direct an imaginary camera to virtually capture natural-looking normal field-of-view (NFOV)…

Strategies that include the generation of synthetic data are beginning to be viable as obtaining real data can be logistically complicated, very expensive or slow. Not only the capture of the data can lead to complications, but also its…

Building realistic wide scale outdoor 3D content with sufficient visual quality to observe at walking eye level or from driven vehicles is often carried out by large teams of artists skilled in modelling, texturing, material shading and…

Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicate this success in visual tasks. Some works attempt to extend this approach to autonomous…

Device-to-device (D2D) communications is one of the key emerging technologies for the fifth generation (5G) networks and beyond. It enables direct communication between mobile users and thereby extends coverage for devices lacking direct…

To enable automated software testing, the ability to automatically navigate to a state of interest and to explore all, or at least sufficient number of, instances of such a state is fundamental. When testing a computer game the problem has…

The field of generative models has recently witnessed significant progress, with diffusion models showing remarkable performance in image generation. In light of this success, there is a growing interest in exploring the application of…

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving. However, manually creating or re-creating real-world-like…

World models can foresee the outcomes of different actions, which is of paramount importance for autonomous driving. Nevertheless, existing driving world models still have limitations in generalization to unseen environments, prediction…

Information visualization is essential in making sense out of large data sets. Often, high-dimensional data are visualized as a collection of points in 2-dimensional space through dimensionality reduction techniques. However, these…

The goal of this paper is to generate simulations with real-world collision scenarios for training and testing autonomous vehicles. We use numerous dashcam crash videos uploaded on the internet to extract valuable collision data and…