Learning with Geometric Priors in U-Net Variants for Polyp Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vazquez, Fabian, Nuñez, Jose A., Adame, Diego, Moreno, Alissen, Zhan, Augustin, Li, Huimin, Yang, Jinghao, Tang, Haoteng, Fu, Bin, Gu, Pengfei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908785580179456
author Vazquez, Fabian
Nuñez, Jose A.
Adame, Diego
Moreno, Alissen
Zhan, Augustin
Li, Huimin
Yang, Jinghao
Tang, Haoteng
Fu, Bin
Gu, Pengfei
author_facet Vazquez, Fabian
Nuñez, Jose A.
Adame, Diego
Moreno, Alissen
Zhan, Augustin
Li, Huimin
Yang, Jinghao
Tang, Haoteng
Fu, Bin
Gu, Pengfei
contents Accurate and robust polyp segmentation is essential for early colorectal cancer detection and for computer-aided diagnosis. While convolutional neural network-, Transformer-, and Mamba-based U-Net variants have achieved strong performance, they still struggle to capture geometric and structural cues, especially in low-contrast or cluttered colonoscopy scenes. To address this challenge, we propose a novel Geometric Prior-guided Module (GPM) that injects explicit geometric priors into U-Net-based architectures for polyp segmentation. Specifically, we fine-tune the Visual Geometry Grounded Transformer (VGGT) on a simulated ColonDepth dataset to estimate depth maps of polyp images tailored to the endoscopic domain. These depth maps are then processed by GPM to encode geometric priors into the encoder's feature maps, where they are further refined using spatial and channel attention mechanisms that emphasize both local spatial and global channel information. GPM is plug-and-play and can be seamlessly integrated into diverse U-Net variants. Extensive experiments on five public polyp segmentation datasets demonstrate consistent gains over three strong baselines. Code and the generated depth maps are available at: https://github.com/fvazqu/GPM-PolypSeg
format Preprint
id arxiv_https___arxiv_org_abs_2601_17331
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning with Geometric Priors in U-Net Variants for Polyp Segmentation
Vazquez, Fabian
Nuñez, Jose A.
Adame, Diego
Moreno, Alissen
Zhan, Augustin
Li, Huimin
Yang, Jinghao
Tang, Haoteng
Fu, Bin
Gu, Pengfei
Computer Vision and Pattern Recognition
Accurate and robust polyp segmentation is essential for early colorectal cancer detection and for computer-aided diagnosis. While convolutional neural network-, Transformer-, and Mamba-based U-Net variants have achieved strong performance, they still struggle to capture geometric and structural cues, especially in low-contrast or cluttered colonoscopy scenes. To address this challenge, we propose a novel Geometric Prior-guided Module (GPM) that injects explicit geometric priors into U-Net-based architectures for polyp segmentation. Specifically, we fine-tune the Visual Geometry Grounded Transformer (VGGT) on a simulated ColonDepth dataset to estimate depth maps of polyp images tailored to the endoscopic domain. These depth maps are then processed by GPM to encode geometric priors into the encoder's feature maps, where they are further refined using spatial and channel attention mechanisms that emphasize both local spatial and global channel information. GPM is plug-and-play and can be seamlessly integrated into diverse U-Net variants. Extensive experiments on five public polyp segmentation datasets demonstrate consistent gains over three strong baselines. Code and the generated depth maps are available at: https://github.com/fvazqu/GPM-PolypSeg
title Learning with Geometric Priors in U-Net Variants for Polyp Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.17331