Related papers: DOGE: Differentiable Bezier Graph Optimization for…
Aiming for higher-level scene understanding, this work presents a neural network approach that takes a road-layout map in bird's-eye-view as input, and predicts a human-interpretable graph that represents the road's topological layout. Our…
Detection of road curbs is an essential capability for autonomous driving. It can be used for autonomous vehicles to determine drivable areas on roads. Usually, road curbs are detected on-line using vehicle-mounted sensors, such as video…
As a parametric polynomial curve family, B\'ezier curves are widely used in safe and smooth motion design of intelligent robotic systems from flying drones to autonomous vehicles to robotic manipulators. In such motion planning settings,…
Node embedding is the task of extracting concise and informative representations of certain entities that are connected in a network. Various real-world networks include information about both node connectivity and certain node attributes,…
Rain streaks bring complicated pixel intensity changes and additional gradients, greatly obstructing the extraction of image features from background. This causes serious performance degradation in feature-based applications. Thus, it is…
One of the most critical pieces of the self-driving puzzle is the task of predicting future movement of surrounding traffic actors, which allows the autonomous vehicle to safely and effectively plan its future route in a complex world.…
This study presents a novel integrated framework for dynamic origin-destination demand estimation (DODE) in multi-class mesoscopic network models, incorporating high-resolution satellite imagery together with conventional traffic data from…
Partial Differential Equations (PDEs) underpin many scientific phenomena, yet traditional computational approaches often struggle with complex, nonlinear systems and irregular geometries. This paper introduces the AMG method, a Multi-Graph…
We introduce a framework for joint grounded scene graph - image generation, a challenging task involving high-dimensional, multi-modal structured data. To effectively model this complex joint distribution, we adopt a factorized approach:…
Document binarization is a key pre-processing step for many document analysis tasks. However, existing methods can not extract stroke edges finely, mainly due to the fair-treatment nature of vanilla convolutions and the extraction of stroke…
Aerodynamic shape optimization has many industrial applications. Existing methods, however, are so computationally demanding that typical engineering practices are to either simply try a limited number of hand-designed shapes or restrict…
Document structure analysis, such as zone segmentation and table recognition, is a complex problem in document processing and is an active area of research. The recent success of deep learning in solving various computer vision and machine…
Autonomous driving requires a structured understanding of the surrounding road network to navigate. One of the most common and useful representation of such an understanding is done in the form of BEV lane graphs. In this work, we use the…
Image tracing is a foundational component of the workflow in graphic design, engineering, and computer animation, linking hand-drawn concept images to collections of smooth curves needed for geometry processing and editing. Even for clean…
LIDAR sensors are usually used to provide autonomous vehicles with 3D representations of their environment. In ideal conditions, geometrical models could detect the road in LIDAR scans, at the cost of a manual tuning of numerical…
Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work…
In image processing, edge detection is a valuable tool to perform the extraction of features from an image. This detection reduces the amount of information to be processed, since the redundant information (considered less relevant) can be…
Automated road network extraction from remote sensing imagery remains a significant challenge despite its importance in a broad array of applications. To this end, we leverage recent open source advances and the high quality SpaceNet…
This paper presents an accurate and fast algorithm for road segmentation using convolutional neural network (CNN) and gated recurrent units (GRU). For autonomous vehicles, road segmentation is a fundamental task that can provide the…
Recently developed deep neural models like NetGAN, CELL, and Variational Graph Autoencoders have made progress but face limitations in replicating key graph statistics on generating large graphs. Diffusion-based methods have emerged as…