37 citations · 63 across the 15 of their papers we have counts for
18 papers
SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination
Athanasios Tragakis, Marco Aversa, Daniela Ivanova +4
SceneHI is a framework that lifts high-resolution, illumination-aware priors from 2D diffusion models to perform 3D texture synthesis. It is the first to demonstrate that high-reso…
IGAF: Incremental Guided Attention Fusion for Depth Super-Resolution
Athanasios Tragakis, Chaitanya Kaul, Kevin J. Mitchell +3
Accurate depth estimation is crucial for many fields, including robotics, navigation, and medical imaging. However, conventional depth sensors often produce low-resolution (LR) dep…
HpEIS: Learning Hand Pose Embeddings for Multimedia Interactive Systems
Songpei Xu, Xuri Ge, Chaitanya Kaul +1
We present a novel Hand-pose Embedding Interactive System (HpEIS) as a virtual sensor, which maps users' flexible hand poses to a two-dimensional visual space using a Variational A…
AI-Enabled sensor fusion of time of flight imaging and mmwave for concealed metal detection
Chaitanya Kaul, Kevin J. Mitchell, Khaled Kassem +6
In the field of detection and ranging, multiple complementary sensing modalities may be used to enrich the information obtained from a dynamic scene. One application of this sensor…
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models
Athanasios Tragakis, Marco Aversa, Chaitanya Kaul +2
In this work, we introduce Pixelsmith, a zero-shot text-to-image generative framework to sample images at higher resolutions with a single GPU. We are the first to show that it is…
GLFNET: Global-Local (frequency) Filter Networks for efficient medical image segmentation
Athanasios Tragakis, Qianying Liu, Chaitanya Kaul +5
We propose a novel transformer-style architecture called Global-Local Filter Network (GLFNet) for medical image segmentation and demonstrate its state-of-the-art performance. We re…
mmSense: Detecting Concealed Weapons with a Miniature Radar Sensor
Kevin Mitchell, Khaled Kassem, Chaitanya Kaul +5
For widespread adoption, public security and surveillance systems must be accurate, portable, compact, and real-time, without impeding the privacy of the individuals being observed…
Continuous interaction with a smart speaker via low-dimensional embeddings of dynamic hand pose
Songpei Xu, Chaitanya Kaul, Xuri Ge +1
This paper presents a new continuous interaction strategy with visual feedback of hand pose and mid-air gesture recognition and control for a smart music speaker, which utilizes on…
Optimizing Vision Transformers for Medical Image Segmentation
Qianying Liu, Chaitanya Kaul, Jun Wang +3
For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture…
The Fully Convolutional Transformer for Medical Image Segmentation
Athanasios Tragakis, Chaitanya Kaul, Roderick Murray-Smith +1
We propose a novel transformer model, capable of segmenting medical images of varying modalities. Challenges posed by the fine grained nature of medical image analysis mean that th…
Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image
Joshua Mitton, Chaitanya Kaul, Roderick Murray-Smith
We develop a rotation equivariant model for generating 3D hand meshes from 2D RGB images. This guarantees that as the input image of a hand is rotated the generated mesh undergoes…
CpT: Convolutional Point Transformer for 3D Point Cloud Processing
Chaitanya Kaul, Joshua Mitton, Hang Dai +1
We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over exi…
Survey: Leakage and Privacy at Inference Time
Marija Jegorova, Chaitanya Kaul, Charlie Mayor +4
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources…
FatNet: A Feature-attentive Network for 3D Point Cloud Processing
Chaitanya Kaul, Nick Pears, Suresh Manandhar
The application of deep learning to 3D point clouds is challenging due to its lack of order. Inspired by the point embeddings of PointNet and the edge embeddings of DGCNNs, we prop…
FocusNet++: Attentive Aggregated Transformations for Efficient and Accurate Medical Image Segmentation
Chaitanya Kaul, Nick Pears, Hang Dai +2
We propose a new residual block for convolutional neural networks and demonstrate its state-of-the-art performance in medical image segmentation. We combine attention mechanisms wi…
Penalizing small errors using an Adaptive Logarithmic Loss
Chaitanya Kaul, Nick Pears, Hang Dai +2
Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth. Fundamentally, they define a functional landscape for travers…
SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing
Chaitanya Kaul, Nick Pears, Suresh Manandhar
Deep neural networks have established themselves as the state-of-the-art methodology in almost all computer vision tasks to date. But their application to processing data lying on…
FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation
Chaitanya Kaul, Suresh Manandhar, Nick Pears
We propose a novel technique to incorporate attention within convolutional neural networks using feature maps generated by a separate convolutional autoencoder. Our attention archi…