中文
相关论文

相关论文: GeoSAM2: Unleashing the Power of SAM2 for 3D Part …

200 篇论文

Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Zhe Zhu , Le Wan , Rui Xu , Yiheng Zhang , Honghua Chen , Zhiyang Dou , Cheng Lin , Yuan Liu , Mingqiang Wei

Medical image segmentation is a crucial and time-consuming task in clinical care, where mask precision is extremely important. The Segment Anything Model (SAM) offers a promising approach, as it provides an interactive interface based on…

计算机视觉与模式识别 · 计算机科学 2025-04-30 Julien Khlaut , Elodie Ferreres , Daniel Tordjman , Hélène Philippe , Tom Boeken , Pierre Manceron , Corentin Dancette

In geographical image segmentation, performance is often constrained by the limited availability of training data and a lack of generalizability, particularly for segmenting mobility infrastructure such as roads, sidewalks, and crosswalks.…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Rafi Ibn Sultan , Chengyin Li , Hui Zhu , Prashant Khanduri , Marco Brocanelli , Dongxiao Zhu

Segment Anything Model (SAM) is one of the pioneering prompt-based foundation models for image segmentation and has been rapidly adopted for various medical imaging applications. However, in clinical settings, creating effective prompts is…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Chengyin Li , Prashant Khanduri , Yao Qiang , Rafi Ibn Sultan , Indrin Chetty , Dongxiao Zhu

Medical images often exhibit distribution shifts due to variations in imaging protocols and scanners across different medical centers. Domain Generalization (DG) methods aim to train models on source domains that can generalize to unseen…

计算机视觉与模式识别 · 计算机科学 2024-11-18 Yihang Fu , Ziyang Chen , Yiwen Ye , Xingliang Lei , Zhisong Wang , Yong Xia

The ability to segment objects based on open-ended language prompts remains a critical challenge, requiring models to ground textual semantics into precise spatial masks while handling diverse and unseen categories. We present OpenWorldSAM,…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Shiting Xiao , Rishabh Kabra , Yuhang Li , Donghyun Lee , Joao Carreira , Priyadarshini Panda

We introduce SAM2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. SAM2Point interprets any 3D data as a series of multi-directional videos, and leverages SAM 2 for…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Ziyu Guo , Renrui Zhang , Xiangyang Zhu , Chengzhuo Tong , Peng Gao , Chunyuan Li , Pheng-Ann Heng

Although new vision foundation models such as Segment Anything Model 2 (SAM2) have significantly enhanced zero-shot image segmentation capabilities, reliance on human-provided prompts poses significant challenges in adapting SAM2 to medical…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Yang Xing , Jiong Wu , Yuheng Bu , Kuang Gong

Segmentation models such as Segment Anything Model (SAM) and SAM2 achieve strong prompt-driven zero-shot performance. However, their training on natural images limits domain transfer to medical data. Consequently, accurate segmentation…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Tal Grossman , Noa Cahan , Lev Ayzenberg , Hayit Greenspan

Advances in machine learning, especially the introduction of transformer architectures and vision transformers, have led to the development of highly capable computer vision foundation models. The segment anything model (known colloquially…

计算机视觉与模式识别 · 计算机科学 2025-05-29 Kenneth Ball , Erin Taylor , Nirav Patel , Andrew Bartels , Gary Koplik , James Polly , Jay Hineman

Segmenting objects with complex shapes, such as wires, bicycles, or structural grids, remains a significant challenge for current segmentation models, including the Segment Anything Model (SAM) and its high-quality variant SAM-HQ. These…

计算机视觉与模式识别 · 计算机科学 2025-06-09 Luka Vetoshkin , Dmitry Yudin

The Segment Anything Model 2 (SAM2) has recently demonstrated exceptional performance in zero-shot prompt segmentation for natural images and videos. However, when the propagation mechanism of SAM2 is applied to medical images, it often…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Yunhao Bai , Boxiang Yun , Zeli Chen , Qinji Yu , Yingda Xia , Yan Wang

Promptable segmentation, introduced by the Segment Anything Model (SAM), is a promising approach for medical imaging, as it enables clinicians to guide and refine model predictions interactively. However, SAM's architecture is designed for…

计算机视觉与模式识别 · 计算机科学 2025-07-11 Théo Danielou , Daniel Tordjman , Pierre Manceron , Corentin Dancette

Segment Anything Model (SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when directly applied to medical image segmentation, since SAM…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Bin Xie , Hao Tang , Bin Duan , Dawen Cai , Yan Yan , Gady Agam

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Xiaoqi Wang , Clint Sebastian , Wenbin He , Liu Ren

The recent Segment Anything Model (SAM) 2 has demonstrated remarkable foundational competence in semantic segmentation, with its memory mechanism and mask decoder further addressing challenges in video tracking and object occlusion, thereby…

计算机视觉与模式识别 · 计算机科学 2024-08-09 Jieming Yu , An Wang , Wenzhen Dong , Mengya Xu , Mobarakol Islam , Jie Wang , Long Bai , Hongliang Ren

The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community. Due to the high similarity between camouflaged objects and…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Xin Zhang , Keren Fu , Qijun Zhao

Promptable segmentation has emerged as a powerful paradigm in computer vision, enabling users to guide models in parsing complex scenes with prompts such as clicks, boxes, or textual cues. Recent advances, exemplified by the Segment…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Yoonwoo Jeong , Cheng Sun , Yu-Chiang Frank Wang , Minsu Cho , Jaesung Choe

Weakly supervised landslide extraction aims to identify landslide regions from remote sensing data using models trained with weak labels, particularly image-level labels. However, it is often challenged by the imprecise boundaries of the…

计算机视觉与模式识别 · 计算机科学 2025-05-23 Jian Wang , Xiaokang Zhang , Xianping Ma , Weikang Yu , Pedram Ghamisi

The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such as non-unified data…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Yuchen Zhou , Jiayuan Gu , Tung Yen Chiang , Fanbo Xiang , Hao Su
‹ 上一页 1 2 3 10 下一页 ›