检索结果-内蒙古大学图书馆

SGIFormer: Semantic-Guided and Geometric-Enhanced Interleaving Transformer for 3d instance segmentation

IEEE TRANSACTIONS ON CIRCUITS ANd SYSTEMS FOR VIdEO TECHNOLOGY 2025年第3期35卷 2276-2288页

作者： Yao, Lei Wang, Yi Liu, Moyun Chau, Lap-Pui Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China

In recent years, transformer-based models have exhibited considerable potential in point cloud instance segmentation. despite the promising performance achieved by existing methods, they encounter challenges such as instance query initialization problems and excessive reliance on stacked layers, rendering them incompatible with large-scale 3d scenes. This paper introduces a novel method, named SGIFormer, for 3d instance segmentation, which is composed of the Semantic-guided Mix Query (SMQ) initialization and the Geometric-enhanced Interleaving Transformer (GIT) decoder. Specifically, the principle of our SMQ initialization scheme is to leverage the predicted voxel-wise semantic information to implicitly generate the scene-aware query, yielding adequate scene prior and compensating for the learnable query set. Subsequently, we feed the formed overall query into our GIT decoder to alternately refine instance query and global scene features for further capturing fine-grained information and reducing complex design intricacies simultaneously. To emphasize geometric property, we consider bias estimation as an auxiliary task and progressively integrate shifted point coordinates embedding to reinforce instance localization. SGIFormer attains state-of-the-art performance on ScanNet V2, ScanNet200, S3dIS datasets, and the challenging high-fidelity ScanNet ++ benchmark, striking a balance between accuracy and efficiency. The code, weights, and demo videos are publicly available at https://***/SGIFormer/.

关键词： Three-dimensional displays Semantics instance segmentation decoding Point cloud compression Pipelines Feature extraction Accuracy Training Point clouds 3d instance segmentation transformer semantic features semantic features

来源：评论

学校读者我要写书评

暂无评论

MLdA-Net: Multi-Level deep Aggregation Network for 3d Nuclei instance segmentation

引用

IEEE JOURNAL OF BIOMEdICAL ANd HEALTH INFORMATICS 2025年第5期29卷 3516-3525页

作者： Hu, Bin Ye, Zhiwei Wei, Zimei Snezhko, Eduard Kovalev, Vassili Ye, Mang Hubei Univ Technol Sch Comp Wuhan 430068 Peoples R China Hubei Prov Key Lab Green Intelligent Comp Power Ne Wuhan 430068 Peoples R China Natl Acad Sci Belarus United Inst Informat Problems Minsk 220012 BELARUS Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China

segmentation of cell nuclei from three-dimensional (3d) volumetric fluorescence microscopy images is crucial for biological and clinical analyses. In recent years, convolutional neural networks have become the reliable 3d medical image segmentation standard. However, convolutional layers are limited by their finite receptive fields and weight-sharing mechanisms. Consequently, they struggle to effectively model long-range dependencies and spatial correlations, which may lead to inadequate nuclei segmentation. Moreover, the diversity in nuclear appearance and density poses additional challenges. This work proposes a lightweight multi-layer deep aggregation network, MLdA-Net, incorporating Wide Receptive Field Attention (WRFA). This module effectively simulates the large receptive field generated by self-attention in the Swin Transformer while requiring fewer model parameters. This design implements an extended global sensory field that enhances the ability to capture a wide range of spatial information. In addition, the multiple cross-attention (MCA) module in MLdA-Net enhances the output features of different resolutions from the encoder while maintaining global effectiveness. The Multi-Path Aggregation Feature Pyramid Network (MAFPN) receives multi-scale outputs from the MCA module, generating a robust hierarchical feature pyramid for the final prediction. MLdA-Net outperforms state-of-the-art networks, including 3dU-Net, nnFormer, UNETR, SwinUNETR, and 3dUXNET, on the 3d volumetric datasets NucMM and MitoEM. It achieves average performance improvements of 4% to 7% in F1 score, MIoU, and PQ metrics, thereby establishing new benchmark results.

关键词： Three-dimensional displays Image segmentation Feature extraction Transformers Computer architecture instance segmentation Bioinformatics Microprocessors Convolution Kernel 3d instance segmentation nuclei segmentation feature aggregation large receptive field deep learning

来源：评论

学校读者我要写书评

暂无评论

GCTransNet: 3d mitochondrial instance segmentation based on Global Context Vision Transformers

引用

JOURNAL OF STRUCTURAL BIOLOGY 2025年第1期217卷 108170页

作者： Chen, Chaoyi Yan, Yidan Wu, Jingpeng Gan, Wen-Biao China Agr Univ Collage Biol Sci Beijing 100091 Peoples R China Shenzhen Bay Lab Shenzhen 518132 Peoples R China Lingang Lab Shanghai 200032 Peoples R China

Mitochondria are double membrane-bound organelles essential for generating energy in eukaryotic cells. Mitochondria can be readily visualized in 3d using Volume Electron Microscopy (vEM), and accurate image segmentation is vital for quantitative analysis of mitochondrial morphology and function. To address the challenge of segmenting small mitochondrial compartments in vEM images, we propose an automated mitochondrial segmentation method called GCTransNet. This method employs grayscale migration technology to preprocess images, effectively reducing intensity distribution differences across EM images. By utilizing 3d Global Context Vision Transformers (GC-ViT) combined with global context self-attention modules and local self-attention modules, GCTransNet precisely models long-range and short-range spatial interactions. The long-range interactions enable the model to capture the global structural relationships within the mitochondrial segmentation network, while the short-range interactions refine local details and boundaries. In our approach, the encoder of the 3d U-Net network, a classical multi-scale learning architecture that retains high-resolution features through skip connections and combines multi-scale features for precise segmentation, is replaced by a 3d GC-ViT. The GC-ViT leverages shifted window-based self-attention, capturing long-range dependencies and offering improved segmentation accuracy compared to traditional U-Net encoders. In the MitoEM mitochondrial segmentation challenge, GCTransNet achieved state-of-the-art results, demonstrating its superiority in automated mitochondrial segmentation. The code and its documentation are publicly available at https://***/GanLab123/G CTransNet.

关键词： Mitochondrial morphology Electron microscopy image 3d instance segmentation Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

YOLO2U-Net: detection-guided 3d instance segmentation for microscopy

引用

PATTERN RECOGNITION LETTERS 2024年 181卷 37-42页

作者： Ziabari, Amirkoushyar Rose, derek C. Shirinifard, Abbas Solecki, david Oak Ridge Natl Lab 5200 1 Bethel Valley Rd Oak Ridge TN 37830 USA St Jude Childrens Res Hosp Memphis TN 37923 USA

Microscopy imaging techniques are instrumental for characterization and analysis of biological structures. As these techniques typically render 3d visualization of cells by stacking 2d projections, issues such as out-of-plane excitation and low resolution in the z-axis may pose challenges (even for human experts) to detect individual cells in 3d volumes as these non-overlapping cells may appear as overlapping. A comprehensive method for accurate 3d instance segmentation of cells in the brain tissue is introduced here. The proposed method combines the 2d YOLO detection method with a multi-view fusion algorithm to construct a 3d localization of the cells. Next, the 3d bounding boxes along with the data volume are input to a 3d U-Net network that is designed to segment the primary cell in each 3d bounding box, and in turn, to carry out instance segmentation of cells in the entire volume. The promising performance of the proposed method is shown in comparison with current deep learning-based 3d instance segmentation methods.

关键词： Cell microscopy 3d instance segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Cd3IS: cross dimensional 3d instance segmentation network for production workshop

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2024年第7期35卷 3273-3289页

作者： Tang, Zaizuo Chen, Guangzhu Wang, Ruili Miao, Zhenlian dai, Manna Ma, Yujun Liao, Xiaojuan Chengdu Univ Technol Coll Comp Sci & Cyber Secur Chengdu Peoples R China Massey Univ Sch Math & Computat Sci Auckland New Zealand ASTAR Inst High Performance Comp Comp & Intelligence Dept Singapore Singapore

Three-dimensional (3d) instance segmentation, as an effective method for scene object recognition, can effectively enhance workshop intelligence. However, the existing 3d instance segmentation network is difficult to apply in workshop scenes due to the large number of 3d instance segmentation labels and 3d information acquisition devices required. In this paper, a monocular 3d instance segmentation network is proposed, which achieves satisfactory results while relying on a monocular RGB camera without 3d instance segmentation labels. The proposed method has two stages. In the first stage, the double-snake multitask network is proposed to solve the problem of a lack of 3d information acquisition devices. It simultaneously performs depth estimation and instance segmentation and uses the features obtained from depth estimation to guide the instance segmentation task. In the second stage, an adaptive point cloud filtering algorithm that performs adaptive point cloud noise filtering on multi-scale objects based on two-dimensional prior information is proposed to solve the problem of a lack of 3d labels. In addition, color information is introduced into the filtering process to further improve filtering accuracy. Experiments on the Cityscapes and SOP datasets demonstrate the competitive performance of the proposed method. When the IoU threshold is set to 0.35, the mean average precision (mAP) is 50.41. Our approach is deployed in an actual production workshop to verify its feasibility.

关键词： 3d instance segmentation depth estimation Multitask learning Production workshop

来源：评论

学校读者我要写书评

暂无评论

C1M2:a universal algorithm for 3d instance segmentation,annotation,and quantification of irregular cells

引用

Science China(Life Sciences) 2023年第10期66卷 2415-2428页

作者： Hao Zheng Songlin Huang Jing Zhang Ren Zhang Jialu Wang Jing Yuan Anan Li Xin Yang Zhihong Zhang Britton Chance Center and MOE Key Laboratory for Biomedical Photonics Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Biomedical Engineering of Hainan Province School of Biomedical EngineeringHainan UniversityHaikou 570228China School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhan 430074China

Cell instance segmentation is a fundamental task for many biological applications,especially for packed cells in three-dimensional(3d)microscope images that can fully display cellular *** processing algorithms based on neural networks and feature engineering have enabled great progress in two-dimensional(2d)instance ***,current methods cannot achieve high segmentation accuracy for irregular cells in 3d *** this study,we introduce a universal,morphology-based 3d instance segmentation algorithm called Crop Once Merge Twice(C1M2),which can segment cells from a wide range of image types and does not require nucleus images.C1M2 can be extended to quantify the fluorescence intensity of fluorescent proteins and antibodies and automatically annotate their expression levels in individual *** results suggest that C1M2 can serve as a tissue cytometry for 3d histopathological assays by quantifying fluorescence intensity with spatial localization and morphological information.

关键词： 3d instance segmentation irregular cells fluorescence images neural networks fluorescence intensity tissue cytometry

来源：评论

学校读者我要写书评

暂无评论

SAM-NeRF: NeRF-Based 3d instance segmentation with Segment Anything Model 33rd

SAM-NeRF: NeRF-Based 3D Instance Segmentation with Segment A...

引用

33rd International Conference on Artificial Neural Networks and Machine Learning (ICANN)

作者： Wang, Xi Xie, Linglin Qiao, Peng dou, Yong Liu, Sidun Li, Wenyu Yang, Kaijun Natl Univ Def Technol Changsha 410073 Peoples R China Second Surveying & Mapping Inst Hunan Changsha 420001 Peoples R China

ISBN: (纸本)9783031723346;9783031723353

Existing NeRF-based instance segmentation methods lift 2d annotated or predicted semantic and instance masks into 3d through radiance field, but still insufficient in segmenting on the unlabeled semantic classes. The Segment Anything Model (SAM) introduces a foundation model for image segmentation, and achieves impressive zero-shot performance. In this paper, we take advantage of SAM and propose SAM-NeRF for 3d instance segmentation agnostic to semantic labels. Unlike existing SAM-based 3d instance segmentation methods which rely on user provided prompts, SAM-NeRF only uses 2d posed images and SAM generated segmentation results to render novel view images with 3d consistent instance masks. To account for the inconsistencies on the instance identifiers across views, we represent the 3d instances with a neural instance field, and propose a mask matching method to lift SAM segmentation results to 3d scene consistently without any semantic supervision. As SAM segments the scene under various granularity, causing divergence cross views, we further propose a merging algorithm to improve the 3d segmentation performance with unified granularity between different views. Without any semantic guidance, our method outperforms the start-of-the-art 2d and 3d supervised panoptic segmentation methods on unlabeled classes in all evaluated datasets.

关键词： 3d instance segmentation NeRF Segment Anything Model Zero-shot segmentation

来源：评论

学校读者我要写书评

暂无评论

UnScene3d: Unsupervised 3d instance segmentation for Indoor Scenes

UnScene3D: Unsupervised 3D Instance Segmentation for Indoor ...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rozenberszki, david Litany, Or dai, Angela Tech Univ Munich Munich Germany Technion Haifa Israel NVIDIA Santa Clara CA USA

ISBN: (纸本)9798350353006

3d instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3d scenes rely on supervision from expensive, manual 3d annotations. We propose UnScene3d, the first fully unsupervised 3d learning approach for class-agnostic 3d instance segmentation of indoor scans. UnScene3d first generates pseudo masks by leveraging self-supervised color and geometry features to find potential object regions. We operate on a basis of geometric oversegmentation, enabling efficient representation and learning on high-resolution 3d data. The coarse proposals are then refined through self-training our model on its predictions. Our approach improves over clustering-based alternatives to unsupervised 3d instance segmentation methods by more than 300% Average Precision score, demonstrating effective instance segmentation even in challenging, cluttered 3d scenes.

关键词： 3d Computer Vision 3d instance segmentation Graph-cuts Scene Understanding Self-training Unsupervised instance segmentation Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

Edge-Aware 3d instance segmentation Network with Intelligent Semantic Prior

Edge-Aware 3D Instance Segmentation Network with Intelligent...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rohl, Wonseok Jung, Hwanhee Nam, Giljoo Yeorn, Jinseop Park, Hyunje Yoon, Sang Ho Kim, Sangpil Korea Univ Seoul South Korea Meta Real Labs Zurich Switzerland Korea Adv Inst Sci & Technol Daejeon South Korea

ISBN: (纸本)9798350353006

While recent 3d instance segmentation approaches show promising results based on transformer architectures, they often fail to correctly identify instances with similar appearances. They also ambiguously determine edges, leading to multiple misclassifications of adjacent edge points. In this work, we introduce a novel framework, called EASE, to overcome these challenges and improve the perception of complex 3d instances. We first propose a semantic guidance network to leverage rich semantic knowledge from a language model as intelligent priors, enhancing the functional understanding of real-world instances beyond relying solely on geometrical information. We explicitly instruct the basic instance queries using text embeddings of each instance to learn deep semantic details. Further, we utilize the edge prediction module, encouraging the segmentation network to be edge-aware. We extract voxel-wise edge maps from point features and use them as auxiliary information for learning edge cues. In our extensive experiments on large-scale benchmarks, ScanNetV2, ScanNet200, S3dIS, and STPLS3d, our EASE outperforms existing state-of-the-art models, demonstrating its superior performance.

关键词： 3d instance segmentation

来源：评论

学校读者我要写书评

暂无评论

MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3d instance segmentation

MaskClustering: View Consensus based Mask Graph Clustering f...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yan, Mi Zhang, Jiazhao Zhu, Yan Wang, He Peking Univ Sch CS CFCS Beijing Peoples R China Beijing Acad Artificial Intelligence Beijing Peoples R China Galbot Shenzhen Peoples R China

ISBN: (纸本)9798350353006

Open-vocabulary 3d instance segmentation is cutting-edge for its ability to segment 3d instances without predefined categories. However, progress in 3d lags behind its 2d counterpart due to limited annotated 3d data. To address this, recent works first generate 2d open-vocabulary masks through 2d models and then merge them into 3d instances based on metrics calculated between two neighboring frames. In contrast to these local metrics, we propose a novel metric, view consensus rate, to enhance the utilization of multi-view observations. The key insight is that two 2d masks should be deemed part of the same 3d instance if a significant number of other 2d masks from different views contain both these two masks. Using this metric as edge weight, we construct a global mask graph where each mask is a node. Through iterative clustering of masks showing high view consensus, we generate a series of clusters, each representing a distinct 3d instance. Notably, our model is training-free. Through extensive experiments on publicly available datasets, including ScanNet++, ScanNet200 and MatterPort3d, we demonstrate that our method achieves state-of-the-art performance in open-vocabulary 3d instance segmentation. Our project page is at https://***/MaskClustering.

关键词： 3d instance segmentation open-vocabulary

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：