Search Results for author:
Found 16 papers, 9 papers with code
Adversarial Data Augmentation via Deformation Statistics
Data augmentation or semi-supervised approaches are commonly used to cope with limited labeled training data.
Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images
We propose a novel transformer-based framework that reconstructs two high fidelity hands from multi-view RGB images.
HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation
In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models.
PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs
Steerable models can provide very general and flexible equivariance by formulating equivariance requirements in the language of representation theory and feature fields, which has been recognized to be effective for many vision tasks.
Fluid registration between lung CT and stationary chest tomosynthesis images
We demonstrate our approach for the registration between CT and stationary chest tomosynthesis (sDCT) images and show how it naturally leads to an iterative image reconstruction approach.
Efficient Equivariant Network
Group equivariant CNNs (G-CNNs) that incorporate more equivariance can significantly improve the performance of conventional CNNs.
Accurate Point Cloud Registration with Robust Optimal Transport
Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric registration of lung vascular trees between inspiration and expiration.
Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models.
PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs
Spherical signals exist in many applications, e. g., planetary data, LiDAR scans and digitalization of 3D objects, calling for models that can process spherical data effectively.
A Deep Network for Joint Registration and Reconstruction of Images with Pathologies
They are therefore not designed for the registration of images with strong pathologies for example in the context of brain tumors, and traumatic brain injuries.
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
In implementation, we discretize the system using the numerical schemes of PDOs, deriving approximately equivariant convolutions (PDO-eConvs).
Ranked #1 on
Image Classification
on MNIST-rot-12
Anatomical Data Augmentation via Fluid-based Image Registration
We introduce a fluid-based image augmentation method for medical image analysis.
Region-specific Diffeomorphic Metric Mapping
We introduce a region-specific diffeomorphic metric mapping (RDMM) registration approach.
Ranked #1 on
Image Registration
on Osteoarthritis Initiative
Networks for Joint Affine and Non-parametric Image Registration
In contrast to existing approaches, our framework combines two registration methods: an affine registration and a vector momentum-parameterized stationary velocity field (vSVF) model.
Ranked #2 on
Image Registration
on Osteoarthritis Initiative
Learning Multi-level Features For Sensor-based Human Action Recognition
This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor.
End-to-End Subtitle Detection and Recognition for Videos in East Asian Languages via CNN Ensemble with Near-Human-Level Performance
In this paper, we propose an innovative end-to-end subtitle detection and recognition system for videos in East Asian languages.
