Search Results for author: Wenming Yang

Found 42 papers, 27 papers with code

DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication

no code implementations3 Feb 2024 Yanjun Liu, Wenming Yang, Qingmin Liao

To fill this gap, we introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks.

Denoising Segmentation +1

LLMRA: Multi-modal Large Language Model based Restoration Assistant

no code implementations21 Jan 2024 Xiaoyu Jin, Yuan Shi, Bin Xia, Wenming Yang

By employing a pretrained multi-modal large language model and a vision language model, we generate text descriptions and encode them as context embedding with degradation information for the degraded image.

Image Restoration Language Modelling +1

Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton

1 code implementation10 Jan 2024 Hongbo Kang, Yong Wang, Mengyuan Liu, Doudou Wu, Peng Liu, Xinlin Yuan, Wenming Yang

To address these two challenges, we propose a diffusion-based refinement framework called DRPose, which refines the output of deterministic models by reverse diffusion and achieves more suitable multi-hypothesis prediction for the current pose benchmark by multi-step refinement with multiple noises.

3D Human Pose Estimation Denoising

RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation

1 code implementation12 Dec 2023 Peng Lu, Tao Jiang, Yining Li, Xiangtai Li, Kai Chen, Wenming Yang

Real-time multi-person pose estimation presents significant challenges in balancing speed and precision.

 Ranked #1 on Multi-Person Pose Estimation on CrowdPose (using extra training data)

Multi-Person Pose Estimation

DSR-Diff: Depth Map Super-Resolution with Diffusion Model

no code implementations16 Nov 2023 Yuan Shi, Bin Xia, Rui Zhu, Qingmin Liao, Wenming Yang

Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and augmented reality.

3D Reconstruction Depth Map Super-Resolution

LAVSS: Location-Guided Audio-Visual Spatial Audio Separation

no code implementations31 Oct 2023 Yuxin Ye, Wenming Yang, Yapeng Tian

LAVSS is inspired by the correlation between spatial audio and visual location.

Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video

1 code implementation ICCV 2023 Xiuzhe Wu, Pengfei Hu, Yang Wu, Xiaoyang Lyu, Yan-Pei Cao, Ying Shan, Wenming Yang, Zhongqian Sun, Xiaojuan Qi

Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training.

Image Generation

DiffI2I: Efficient Diffusion Model for Image-to-Image Translation

no code implementations26 Aug 2023 Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xinglong Wu, Yapeng Tian, Wenming Yang, Radu Timotfe, Luc van Gool

Compared to traditional DMs, the compact IPR enables DiffI2I to obtain more accurate outcomes and employ a lighter denoising network and fewer iterations.

Denoising Image-to-Image Translation +2

Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression

1 code implementation15 Aug 2023 Yue Lv, Jinxi Xiang, Jun Zhang, Wenming Yang, Xiao Han, Wei Yang

We thus introduce a dynamic gating network on top of the low-rank adaptation method, in order to decide which decoder layer should employ adaptation.

Image Compression

Double-chain Constraints for 3D Human Pose Estimation in Images and Videos

1 code implementation10 Aug 2023 Hongbo Kang, Yong Wang, Mengyuan Liu, Doudou Wu, Peng Liu, Wenming Yang

Notably, our model achieves state-of-the-art performance on all action categories in the Human3. 6M dataset using detected 2D poses from CPN, and our code is available at: https://github. com/KHB1698/DC-GCT.

Monocular 3D Human Pose Estimation

Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes

1 code implementation IEEE ROBOTICS AND AUTOMATION LETTERS 2023 Siang Chen, Wei Tang, Pengwei Xie, Wenming Yang, Guijin Wang

Specifically, Gaussian encoding and the grid-based strategy are applied to predict grasp heatmaps as guidance to aggregate local points into graspable regions and provide global semantic information.

Grasp Generation Robotic Grasping

Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI

1 code implementation5 Jul 2023 Jiamiao Zhang, Yichen Chi, Jun Lyu, Wenming Yang, Yapeng Tian

Limited by imaging systems, the reconstruction of Magnetic Resonance Imaging (MRI) images from partial measurement is essential to medical imaging research.


Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution

no code implementations29 May 2023 Ruofan Zhang, Jinjin Gu, Haoyu Chen, Chao Dong, Yulun Zhang, Wenming Yang

In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images.


EgoVSR: Towards High-Quality Egocentric Video Super-Resolution

1 code implementation24 May 2023 Yichen Chi, Junhao Gu, Jiamiao Zhang, Wenming Yang, Yapeng Tian

We explicitly tackle motion blurs in egocentric videos using a Dual Branch Deblur Network (DB$^2$Net) in the VSR framework.

Video Super-Resolution

DiffIR: Efficient Diffusion Model for Image Restoration

1 code implementation ICCV 2023 Bin Xia, Yulun Zhang, Shiyin Wang, Yitong Wang, Xinglong Wu, Yapeng Tian, Wenming Yang, Luc van Gool

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network.

Denoising Image Generation +1

Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection

no code implementations13 Feb 2023 Yanjun Liu, Wenming Yang

Instead of using ground-truth labels as direct supervision, our relative and corner loss are derived from the homogeneous transformation, which renders the model to learn the geometric consistency between objects.

3D Object Detection Graph Generation +5

MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring

no code implementations28 Jan 2023 Yuzhen Qin, Li Sun, Hui Chen, Wei-Qiang Zhang, Wenming Yang, Jintao Fei, Guijin Wang

However, it is challenging to develop a single-lead-based ECG interpretation model for multiple diseases diagnosis due to the lack of some key disease information.

ECG Classification Knowledge Distillation

Local and Global Logit Adjustments for Long-Tailed Learning

no code implementations ICCV 2023 Yingfan Tao, Jingna Sun, Hao Yang, Li Chen, Xu Wang, Wenming Yang, Daniel Du, Min Zheng

LGLA consists of two core components: a Class-aware Logit Adjustment (CLA) strategy and an Adaptive Angular Weighted (AAW) loss.

A Dual-scale Lead-seperated Transformer With Lead-orthogonal Attention And Meta-information For Ecg Classification

no code implementations23 Nov 2022 Yang Li, Guijin Wang, Zhourui Xia, Wenming Yang, Li Sun

Auxiliary diagnosis of cardiac electrophysiological status can be obtained through the analysis of 12-lead electrocardiograms (ECGs).

ECG Classification

Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images

no code implementations9 Oct 2022 Jinjin Gu, Haoming Cai, Chenyu Dong, Ruofan Zhang, Yulun Zhang, Wenming Yang, Chun Yuan

We finally use a guided fusion operation to integrate the sharp edges generated by the network and flat areas by the interpolation method to get the final SR image.

Quantization Super-Resolution

Basic Binary Convolution Unit for Binarized Image Restoration Network

2 code implementations2 Oct 2022 Bin Xia, Yulun Zhang, Yitong Wang, Yapeng Tian, Wenming Yang, Radu Timofte, Luc van Gool

In this study, we reconsider components in binary convolution, such as residual connection, BatchNorm, activation function, and structure, for IR tasks.

Binarization Image Restoration +1

Structured Sparsity Learning for Efficient Video Super-Resolution

1 code implementation CVPR 2023 Bin Xia, Jingwen He, Yulun Zhang, Yitong Wang, Yapeng Tian, Wenming Yang, Luc van Gool

In SSL, we design pruning schemes for several key components in VSR models, including residual blocks, recurrent networks, and upsampling networks.

Video Super-Resolution

SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization

1 code implementation CVPR 2022 Yucheng Hang, Bin Xia, Wenming Yang, Qingmin Liao

In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity.

Contrastive Learning Image Harmonization

STDAN: Deformable Attention Network for Space-Time Video Super-Resolution

1 code implementation14 Mar 2022 Hai Wang, Xiaoyu Xiang, Yapeng Tian, Wenming Yang, Qingmin Liao

Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction.

Space-time Video Super-resolution Video Super-Resolution

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution

1 code implementation12 Jan 2022 Bin Xia, Yapeng Tian, Yucheng Hang, Wenming Yang, Qingmin Liao, Jie zhou

To improve matching efficiency, we design a novel Embedded PatchMacth scheme with random samples propagation, which involves end-to-end training with asymptotic linear computational cost to the input size.

Reference-based Super-Resolution

Efficient Non-Local Contrastive Attention for Image Super-Resolution

1 code implementation11 Jan 2022 Bin Xia, Yucheng Hang, Yapeng Tian, Wenming Yang, Qingmin Liao, Jie zhou

To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone.

Contrastive Learning Image Super-Resolution

ER-IQA: Boosting Perceptual Quality Assessment Using External Reference Images

no code implementations6 May 2021 Jingyu Guo, Wei Wang, Wenming Yang, Qingmin Liao, Jie zhou

In this paper, we introduce a brand new scheme, namely external-reference image quality assessment (ER-IQA), by introducing external reference images to bridge the gap between FR and NR-IQA.

Image Quality Assessment NR-IQA

Attention Cube Network for Image Restoration

1 code implementation13 Sep 2020 Yucheng Hang, Qingmin Liao, Wenming Yang, Yupeng Chen, Jie zhou

The adaptive spatial attention branch (ASAB) and the adaptive channel attention branch (ACAB) constitute the adaptive dual attention module (ADAM), which can capture the long-range spatial and channel-wise contextual information to expand the receptive field and distinguish different types of information for more effective feature representations.

Image Restoration

Real-MFF: A Large Realistic Multi-focus Image Dataset with Ground Truth

no code implementations28 Mar 2020 Juncheng Zhang, Qingmin Liao, Shaojun Liu, Haoyu Ma, Wenming Yang, Jing-Hao Xue

In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images.

LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution

1 code implementation9 Sep 2019 Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, Qingmin Liao

In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution.

Image Super-Resolution

CFSNet: Toward a Controllable Feature Space for Image Restoration

1 code implementation ICCV 2019 Wei Wang, Ruiming Guo, Yapeng Tian, Wenming Yang

Deep learning methods have witnessed the great progress in image restoration with specific metrics (e. g., PSNR, SSIM).

Image Restoration Image Super-Resolution +1

Lightweight Feature Fusion Network for Single Image Super-Resolution

2 code implementations15 Feb 2019 Wenming Yang, Wei Wang, Xuechen Zhang, Shuifa Sun, Qingmin Liao

Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit.

Image Super-Resolution

Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax

1 code implementation11 Dec 2018 Peng Lu, Gao Huang, Hangyu Lin, Wenming Yang, Guodong Guo, Yanwei Fu

This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation.

Retrieval Sketch-Based Image Retrieval

Deep Learning for Single Image Super-Resolution: A Brief Review

1 code implementation9 Aug 2018 Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions.

Efficient Neural Network Image Super-Resolution

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