Alexandra Carlson
YOU?
Author Swipe
View article: Proceedings of the Workshop on 3D Geometry Generation for Scientific Computing
Proceedings of the Workshop on 3D Geometry Generation for Scientific Computing Open
High-fidelity 3D geometries of the natural and built world around us are an essential part of answering some of the most pressing scientific questions of our day. Through advances in deep learning, computer vision, and artificial intellige…
View article: Author Index
Author Index Open
View article: LANe: Lighting-Aware Neural Fields for Compositional Scene Synthesis
LANe: Lighting-Aware Neural Fields for Compositional Scene Synthesis Open
Neural fields have recently enjoyed great success in representing and rendering 3D scenes. However, most state-of-the-art implicit representations model static or dynamic scenes as a whole, with minor variations. Existing work on learning …
View article: CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations
CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations Open
Recent advances in neural radiance fields (NeRFs) achieve state-of-the-art novel view synthesis and facilitate dense estimation of scene properties. However, NeRFs often fail for large, unbounded scenes that are captured under very sparse …
View article: Intelligent Deep Data Generation in 2D and 3D
Intelligent Deep Data Generation in 2D and 3D Open
Deep Convolutional Neural Networks, which are a family of biologically inspired machine vision algorithms, have become ubiquitous in perception systems for autonomous agents due to their ability to accurately perform complex tasks and lear…
View article: 3D Graph Convolutional Neural Networks in Architecture Design
3D Graph Convolutional Neural Networks in Architecture Design Open
The nature of the architectural design process can be described along the lines of the following representational devices: the plan and the model.Plans can be considered one of the oldest methods to represent spatial and aesthetic informat…
View article: How Machines Learn to Plan
How Machines Learn to Plan Open
This paper strives to interrogate the abilities of machine vision techniques based on a family of deep neural networks, called generative adversarial neural networks (GANs), to devise alternative planning solutions.The basis for these proc…
View article: Shadow Transfer: Single Image Relighting For Urban Road Scenes
Shadow Transfer: Single Image Relighting For Urban Road Scenes Open
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 sce…
View article: Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation
Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation Open
Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain shift that can occur between two different datasets. This d…
View article: Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for\n Sim-to-Real Domain Adaptation
Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for\n Sim-to-Real Domain Adaptation Open
Performance on benchmark datasets has drastically improved with advances in\ndeep learning. Still, cross-dataset generalization performance remains\nrelatively low due to the domain shift that can occur between two different\ndatasets. Thi…
View article: Modeling Camera Effects to Improve Visual Learning from Synthetic Data
Modeling Camera Effects to Improve Visual Learning from Synthetic Data Open
Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and wea…
View article: Modeling Camera Effects to Improve Deep Vision for Real and Synthetic Data
Modeling Camera Effects to Improve Deep Vision for Real and Synthetic Data Open
Recent work has focused on generating synthetic imagery and augmenting real imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or v…