Cover Image

FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Qiang, Zhou, Ying, Ji, Gepeng, Barnes, Nick, Li, Qiang, Wang, Zhiwei
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

First-frame Supervised Video Polyp Segmentation via Propagative and Semantic Dual-teacher Network
by: Hu, Qiang, et al.
Published: (2024)

SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation
by: Hu, Qiang, et al.
Published: (2024)

MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint
by: Hu, Qiang, et al.
Published: (2024)

Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation
by: Yin, Ming, et al.
Published: (2025)

RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp Segmentation
by: Lin, Weikun, et al.
Published: (2026)

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
by: Ding, Shuangrui, et al.
Published: (2024)

Holistic White-light Polyp Classification via Alignment-free Dense Distillation of Auxiliary Optical Chromoendoscopy
by: Hu, Qiang, et al.
Published: (2025)

One Polyp Identifies All: One-Shot Polyp Segmentation with SAM via Cascaded Priors and Iterative Prompt Evolution
by: Mao, Xinyu, et al.
Published: (2025)

E-SAM: Training-Free Segment Every Entity Model
by: Zhang, Weiming, et al.
Published: (2025)

Diff-VPS: Video Polyp Segmentation via a Multi-task Diffusion Network with Adversarial Temporal Reasoning
by: Lu, Yingling, et al.
Published: (2024)

IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors
by: Wang, Zhiwei, et al.
Published: (2023)

Targeted False Positive Synthesis via Detector-guided Adversarial Diffusion Attacker for Robust Polyp Detection
by: Zhou, Quan, et al.
Published: (2025)

Rethinking Polyp Segmentation from an Out-of-Distribution Perspective
by: Ji, Ge-Peng, et al.
Published: (2023)

A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
by: Ding, Haoxuan, et al.
Published: (2024)

Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation
by: Karmann, Markus, et al.
Published: (2024)

Repurposing SAM for User-Defined Semantics Aware Segmentation
by: Kundu, Rohit, et al.
Published: (2023)

SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp Segmentation
by: Dutta, Tapas Kumar, et al.
Published: (2024)

DiffuSAM: Diffusion-Based Prompt-Free SAM2 for Few-Shot and Source-Free Medical Image Segmentation
by: Grossman, Tal, et al.
Published: (2026)

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
by: Lin, Zhiwei, et al.
Published: (2024)

Training-Free Robust Interactive Video Object Segmentation
by: Wei, Xiaoli, et al.
Published: (2024)

PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation
by: Rahman, Md Mostafijur, et al.
Published: (2024)

SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation
by: Trinh, Quoc-Huy, et al.
Published: (2024)

MirrorSAM2: Segment Mirror in Videos with Depth Perception
by: Xu, Mingchen, et al.
Published: (2025)

Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detection
by: Mansoori, Mobina, et al.
Published: (2024)

Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection
by: Zhang, Xin, et al.
Published: (2024)

Progressively Normalized Self-Attention Network for Video Polyp Segmentation
by: Ji, Ge-Peng, et al.
Published: (2021)

SAM4D: Segment Anything in Camera and LiDAR Streams
by: Xu, Jianyun, et al.
Published: (2025)

InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
by: Zheng, Yijie, et al.
Published: (2025)

Biomedical SAM 2: Segment Anything in Biomedical Images and Videos
by: Yan, Zhiling, et al.
Published: (2024)

SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation
by: Shrestha, Sahir, et al.
Published: (2024)

SAM3-I: Segment Anything with Instructions
by: Li, Jingjing, et al.
Published: (2025)

DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentation
by: Gao, Yifan, et al.
Published: (2023)

From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation
by: Agnihotri, Shivanshu, et al.
Published: (2025)

BachVid: Training-Free Video Generation with Consistent Background and Character
by: Yan, Han, et al.
Published: (2025)

MixPolyp: Integrating Mask, Box and Scribble Supervision for Enhanced Polyp Segmentation
by: Hu, Yiwen, et al.
Published: (2024)

MAST: Video Polyp Segmentation with a Mixture-Attention Siamese Transformer
by: Chen, Geng, et al.
Published: (2024)

Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation
by: Yu, Qiyang, et al.
Published: (2025)

Moving Light Adaptive Colonoscopy Reconstruction via Illumination-Attenuation-Aware 3D Gaussian Splatting
by: Wang, Hao, et al.
Published: (2025)

Pairing-free Group-level Knowledge Distillation for Robust Gastrointestinal Lesion Classification in White-Light Endoscopy
by: Hu, Qiang, et al.
Published: (2026)

SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost
by: Mei, Haiyang, et al.
Published: (2025)