Search Results for author: Yihao Liu

Found 47 papers, 19 papers with code

Segment Any Medical Model Extended

no code implementations26 Mar 2024 Yihao Liu, Jiaming Zhang, Andres Diaz-Pinto, Haowei Li, Alejandro Martin-Gomez, Amir Kheradmand, Mehran Armand

To this end, a unified platform helps push the boundary of the foundation model for medical images, facilitating the use, modification, and validation of SAM and its variants in medical image segmentation.

Realtime Robust Shape Estimation of Deformable Linear Object

no code implementations24 Mar 2024 Jiaming Zhang, Zhaomeng Zhang, Yihao Liu, Yaqian Chen, Amir Kheradmand, Mehran Armand

We propose a robust method to estimate the shape of linear deformable objects in realtime using scattered and unordered key points.

Object Unity

A Roadmap Towards Automated and Regulated Robotic Systems

no code implementations21 Mar 2024 Yihao Liu, Mehran Armand

The rapid development of generative technology opens up possibility for higher level of automation, and artificial intelligence (AI) embodiment in robotic systems is imminent.

SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model

1 code implementation13 Mar 2024 Yihao Liu, Feng Xue, Anlong Ming

Third, to reduce the reliance on massive training data, we propose a ``divide and conquer" solution.

Depth Estimation

From Registration Uncertainty to Segmentation Uncertainty

no code implementations8 Mar 2024 Junyu Chen, Yihao Liu, Shuwen Wei, Zhangxing Bian, Aaron Carass, Yong Du

Here, we propose a novel framework to concurrently estimate both the epistemic and aleatoric segmentation uncertainties for image registration.

Image Registration Segmentation

Revisiting registration-based synthesis: A focus on unsupervised MR image synthesis

no code implementations19 Feb 2024 Savannah P. Hays, Lianrui Zuo, Yihao Liu, Anqi Feng, Jiachen Zhuo, Jerry L. Prince, Aaron Carass

Subsequently, this estimated deformation is applied to align the paired WMn counterpart of the moving CSFn image, yielding a synthetic WMn image for the fixed CSFn image.

Anatomy Image Registration +1

Learning to See Low-Light Images via Feature Domain Adaptation

no code implementations11 Dec 2023 Qirui Yang, Qihua Cheng, Huanjing Yue, Le Zhang, Yihao Liu, Jingyu Yang

To solve this problem, we propose a single-stage network empowered by Feature Domain Adaptation (FDA) to decouple the denoising and color mapping tasks in raw LLIE.

Denoising Domain Adaptation +1

A Comparative Study of Image Restoration Networks for General Backbone Network Design

1 code implementation18 Oct 2023 Xiangyu Chen, Zheyuan Li, Yuandong Pu, Yihao Liu, Jiantao Zhou, Yu Qiao, Chao Dong

Following this, we present the benchmark results and analyze the reasons behind the performance disparity of different models across various tasks.

Image Restoration

Unifying Image Processing as Visual Prompting Question Answering

no code implementations16 Oct 2023 Yihao Liu, Xiangyu Chen, Xianzheng Ma, Xintao Wang, Jiantao Zhou, Yu Qiao, Chao Dong

To address this issue, we propose a universal model for general image processing that covers image restoration, image enhancement, image feature extraction tasks, etc.

Image Enhancement Image Restoration +4

MomentaMorph: Unsupervised Spatial-Temporal Registration with Momenta, Shooting, and Correction

no code implementations5 Aug 2023 Zhangxing Bian, Shuwen Wei, Yihao Liu, Junyu Chen, Jiachen Zhuo, Fangxu Xing, Jonghye Woo, Aaron Carass, Jerry L. Prince

We introduce a novel "momenta, shooting, and correction" framework for Lagrangian motion estimation in the presence of repetitive patterns and large motion.

Motion Estimation

LeCo: Lightweight Compression via Learning Serial Correlations

no code implementations27 Jun 2023 Yihao Liu, Xinyu Zeng, Huanchen Zhang

Lightweight data compression is a key technique that allows column stores to exhibit superior performance for analytical queries.

Data Compression

EVD Surgical Guidance with Retro-Reflective Tool Tracking and Spatial Reconstruction using Head-Mounted Augmented Reality Device

no code implementations27 Jun 2023 Haowei Li, Wenqing Yan, Du Liu, Long Qian, Yuxing Yang, Yihao Liu, Zhe Zhao, Hui Ding, Guangzhi Wang

The head surface is reconstructed using depth data for spatial registration, avoiding fixing tracking targets rigidly on the patient's skull.

Anatomy

Joint Denoising and Fusion with Short- and Long-exposure Raw Pairs

no code implementations17 Jun 2023 Qirui Yang, Yihao Liu, Qihua Chen, Jingyu Yang

Current methods predominantly generate HDR images from a set of bracketed exposure sRGB images.

Denoising HDR Reconstruction

SAMM (Segment Any Medical Model): A 3D Slicer Integration to SAM

1 code implementation12 Apr 2023 Yihao Liu, Jiaming Zhang, Zhangcong She, Amir Kheradmand, Mehran Armand

To assist with the development, assessment, and application of SAM on medical images, we introduce Segment Any Medical Model (SAMM), an extension of SAM on 3D Slicer - an image processing and visualization software extensively used by the medical imaging community.

Image Segmentation Segmentation +1

Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

1 code implementation CVPR 2023 Wenteng Liang, Feng Xue, Yihao Liu, Guofeng Zhong, Anlong Ming

The recently proposed open-world object and open-set detection have achieved a breakthrough in finding never-seen-before objects and distinguishing them from known ones.

Object object-detection +2

Masked Image Training for Generalizable Deep Image Denoising

1 code implementation CVPR 2023 Haoyu Chen, Jinjin Gu, Yihao Liu, Salma Abdel Magid, Chao Dong, Qiong Wang, Hanspeter Pfister, Lei Zhu

To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training.

Image Denoising

Spatially-varying Regularization with Conditional Transformer for Unsupervised Image Registration

no code implementations10 Mar 2023 Junyu Chen, Yihao Liu, Yufan He, Yong Du

In the past, optimization-based registration models have used spatially-varying regularization to account for deformation variations in different image regions.

Image Registration

Deformable Cross-Attention Transformer for Medical Image Registration

no code implementations10 Mar 2023 Junyu Chen, Yihao Liu, Yufan He, Yong Du

Transformers have recently shown promise for medical image applications, leading to an increasing interest in developing such models for medical image registration.

Image Registration Medical Image Registration

Automated Ventricle Parcellation and Evan's Ratio Computation in Pre- and Post-Surgical Ventriculomegaly

no code implementations3 Mar 2023 Yuli Wang, Anqi Feng, Yuan Xue, Lianrui Zuo, Yihao Liu, Ari M. Blitz, Mark G. Luciano, Aaron Carass, Jerry L. Prince

Normal pressure hydrocephalus~(NPH) is a brain disorder associated with enlarged ventricles and multiple cognitive and motor symptoms.

Management

A latent space for unsupervised MR image quality control via artifact assessment

no code implementations1 Feb 2023 Lianrui Zuo, Yuan Xue, Blake E. Dewey, Yihao Liu, Jerry L. Prince, Aaron Carass

Image quality control (IQC) can be used in automated magnetic resonance (MR) image analysis to exclude erroneous results caused by poorly acquired or artifact-laden images.

Contrastive Learning

DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue

1 code implementation18 Jan 2023 Zhangxing Bian, Fangxu Xing, Jinglun Yu, Muhan Shao, Yihao Liu, Aaron Carass, Jiachen Zhuo, Jonghye Woo, Jerry L. Prince

We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion.

Motion Estimation TAG

DegAE: A New Pretraining Paradigm for Low-Level Vision

1 code implementation CVPR 2023 Yihao Liu, Jingwen He, Jinjin Gu, Xiangtao Kong, Yu Qiao, Chao Dong

However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging.

Philosophy

On Finite Difference Jacobian Computation in Deformable Image Registration

1 code implementation12 Dec 2022 Yihao Liu, Junyu Chen, Shuwen Wei, Aaron Carass, Jerry Prince

For digital transformations, |J| is commonly approximated using a central difference, but this strategy can yield positive |J|'s for transformations that are clearly not diffeomorphic -- even at the voxel resolution level.

Image Registration

Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis

1 code implementation2 Oct 2022 Haomiao Ni, Yihao Liu, Sharon X. Huang, Yuan Xue

The novel design of dual branches combines the strengths of deformation-grid-based transformation and warp-free generation for better identity preservation and robustness to occlusion in the synthesized videos.

motion retargeting

CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm

no code implementations12 Jul 2022 Mingye Xu, Yali Wang, Yihao Liu, Tong He, Yu Qiao

Inspired by prompting approaches from NLP, we creatively reinterpret point cloud generation and refinement as the prompting and predicting stages, respectively.

Point Cloud Completion

Evaluating the Generalization Ability of Super-Resolution Networks

no code implementations14 May 2022 Yihao Liu, Hengyuan Zhao, Jinjin Gu, Yu Qiao, Chao Dong

However, research on the generalization ability of Super-Resolution (SR) networks is currently absent.

Super-Resolution

A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds

no code implementations10 May 2022 Wenlong Zhang, Guangyuan Shi, Yihao Liu, Chao Dong, Xiao-Ming Wu

The recently proposed practical degradation model includes a full spectrum of degradation types, but only considers complex cases that use all degradation types in the degradation process, while ignoring many important corner cases that are common in the real world.

Blind Super-Resolution Super-Resolution

Disentangling A Single MR Modality

no code implementations10 May 2022 Lianrui Zuo, Yihao Liu, Yuan Xue, Shuo Han, Murat Bilgel, Susan M. Resnick, Jerry L. Prince, Aaron Carass

Disentangling anatomical and contrast information from medical images has gained attention recently, demonstrating benefits for various image analysis tasks.

Anatomy Disentanglement +3

Coordinate Translator for Learning Deformable Medical Image Registration

1 code implementation5 Mar 2022 Yihao Liu, Lianrui Zuo, Shuo Han, Yuan Xue, Jerry L. Prince, Aaron Carass

The majority of deep learning (DL) based deformable image registration methods use convolutional neural networks (CNNs) to estimate displacement fields from pairs of moving and fixed images.

Deformable Medical Image Registration Image Registration +1

Learn to Match: Automatic Matching Network Design for Visual Tracking

1 code implementation ICCV 2021 Zhipeng Zhang, Yihao Liu, Xiao Wang, Bing Li, Weiming Hu

Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants.

Visual Tracking

RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank

no code implementations20 Jul 2021 Wenlong Zhang, Yihao Liu, Chao Dong, Yu Qiao

To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of different perceptual metrics.

Image Super-Resolution Learning-To-Rank

Blind Image Super-Resolution: A Survey and Beyond

no code implementations7 Jul 2021 Anran Liu, Yihao Liu, Jinjin Gu, Yu Qiao, Chao Dong

This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used for solving the SR model.

Image Super-Resolution

Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings

3 code implementations15 Jun 2021 Hengyuan Zhao, Wenhao Wu, Yihao Liu, Dongliang He

In this paper, we present a fast exemplar-based image colorization approach using color embeddings named Color2Embed.

Colorization Image Colorization +1

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

1 code implementation27 May 2021 Xiangyu Chen, Yihao Liu, Zhengwen Zhang, Yu Qiao, Chao Dong

In this work, we propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization.

Denoising HDR Reconstruction +2

Conditional Sequential Modulation for Efficient Global Image Retouching

1 code implementation ECCV 2020 Jingwen He, Yihao Liu, Yu Qiao, Chao Dong

The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector.

Image Retouching Photo Retouching

Enhanced Quadratic Video Interpolation

2 code implementations10 Sep 2020 Yihao Liu, Liangbin Xie, Li Si-Yao, Wenxiu Sun, Yu Qiao, Chao Dong

In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model.

Super-Resolution Video Frame Interpolation

FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing

no code implementations20 Jan 2020 Yu Dong, Yihao Liu, He Zhang, Shifeng Chen, Yu Qiao

With the proposed Fusion-discriminator which takes frequency information as additional priors, our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts.

Image Dehazing Single Image Dehazing

RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution

2 code implementations ICCV 2019 Wenlong Zhang, Yihao Liu, Chao Dong, Yu Qiao

To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of perceptual metrics.

Image Super-Resolution

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

45 code implementations1 Sep 2018 Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang

To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).

Face Hallucination Generative Adversarial Network +2

Cannot find the paper you are looking for? You can Submit a new open access paper.