27 citations · 80 across the 18 of their papers we have counts for
18 papers
Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
Lechun You, Zhonghua Wu, Weide Liu +5
Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud…
IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter
Xiaojing Zhong, Zhonghua Wu, Xiaofeng Yang +2
Given a pair of images depicting a person and a garment separately, image-based 3D virtual try-on methods aim to reconstruct a 3D human model that realistically portrays the person…
DI-Net : Decomposed Implicit Garment Transfer Network for Digital Clothed 3D Human
Xiaojing Zhong, Yukun Su, Zhonghua Wu +2
3D virtual try-on enjoys many potential applications and hence has attracted wide attention. However, it remains a challenging task that has not been adequately solved. Existing 2D…
SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization
Xiaojing Zhong, Xinyi Huang, Zhonghua Wu +2
Makeup transfer is a process of transferring the makeup style from a reference image to the source images, while preserving the source images' identities. This technique is highly…
LCReg: Long-Tailed Image Classification with Latent Categories based Recognition
Weide Liu, Zhonghua Wu, Yiming Wang +4
In this work, we tackle the challenging problem of long-tailed image recognition. Previous long-tailed recognition approaches mainly focus on data augmentation or re-balancing stra…
CoactSeg: Learning from Heterogeneous Data for New Multiple Sclerosis Lesion Segmentation
Yicheng Wu, Zhonghua Wu, Hengcan Shi +3
New lesion segmentation is essential to estimate the disease progression and therapeutic effects during multiple sclerosis (MS) clinical treatments. However, the expensive data acq…
Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation
Weide Liu, Zhonghua Wu, Yang Zhao +4
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome th…
Modeling Continuous Motion for 3D Point Cloud Object Tracking
Zhipeng Luo, Gongjie Zhang, Changqing Zhou +4
The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have…
Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation
Zhonghua Wu, Yicheng Wu, Guosheng Lin +1
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper…
Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation
Zhonghua Wu, Yicheng Wu, Guosheng Lin +2
Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy bu…
Long-tailed Recognition by Learning from Latent Categories
Weide Liu, Zhonghua Wu, Yiming Wang +4
In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing str…
Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation
Yicheng Wu, Zhonghua Wu, Qianyi Wu +2
Semi-supervised segmentation remains challenging in medical imaging since the amount of annotated medical data is often scarce and there are many blurred pixels near the adhesive e…
MV-TON: Memory-based Video Virtual Try-on network
Xiaojing Zhong, Zhonghua Wu, Taizhe Tan +2
With the development of Generative Adversarial Network, image-based virtual try-on methods have made great progress. However, limited work has explored the task of video-based virt…
Learning Meta-class Memory for Few-Shot Semantic Segmentation
Zhonghua Wu, Xiangxi Shi, Guosheng lin +1
Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. I…
Few-Shot Segmentation with Global and Local Contrastive Learning
Weide Liu, Zhonghua Wu, Henghui Ding +4
In this work, we address the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query…
Remember What You have drawn: Semantic Image Manipulation with Memory
Xiangxi Shi, Zhonghua Wu, Guosheng Lin +2
Image manipulation with natural language, which aims to manipulate images with the guidance of language descriptions, has been a challenging problem in the fields of computer visio…
Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection
Zhonghua Wu, Qingyi Tao, Guosheng Lin +1
Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To…
M2E-Try On Net: Fashion from Model to Everyone
Zhonghua Wu, Guosheng Lin, Qingyi Tao +1
Most existing virtual try-on applications require clean clothes images. Instead, we present a novel virtual Try-On network, M2E-Try On Net, which transfers the clothes from a model…