Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimation

• URL: http://arxiv.org/abs/2603.15374v1
• Date: Mon, 16 Mar 2026 14:50:22 GMT
• Title: Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimation
• Abstract summary: Foundation models trained on natural images fail to generalize directly to colonoscopy.<n>We propose SpecDepth, a parameter-efficient adaptation framework that preserves the robust geometric representations of the pre-trained models.<n>On the public C3VD and SimCol3D datasets, SpecDepth achieved state-of-the-art performance with an absolute relative error of 0.022 and 0.027.
• Score: 6.285139034905719
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Accurate monocular depth estimation is critical in colonoscopy for lesion localization and navigation. Foundation models trained on natural images fail to generalize directly to colonoscopy. We identify the core issue not as a semantic gap, but as a statistical shift in the frequency domain: colonoscopy images lack the strong high-frequency edge and texture gradients that these models rely on for geometric reasoning. To address this, we propose SpecDepth, a parameter-efficient adaptation framework that preserves the robust geometric representations of the pre-trained models while adapting to the colonoscopy domain. Its key innovation is an adaptive spectral rectification module, which uses a learnable wavelet decomposition to explicitly model and amplify the attenuated high-frequency components in feature maps. Different from conventional fine-tuning that risks distorting high-level semantic features, this targeted, low-level adjustment realigns the input signal with the original inductive bias of the foundational model. On the public C3VD and SimCol3D datasets, SpecDepth achieved state-of-the-art performance with an absolute relative error of 0.022 and 0.027, respectively. Our work demonstrates that directly addressing spectral mismatches is a highly effective strategy for adapting vision foundation models to specialized medical imaging tasks. The code will be released publicly after the manuscript is accepted for publication.

Related papers

• Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection [52.986874008247554]
  We propose ReCAP, a language-free framework that replaces static anchors with input-conditioned visual prototypes.<n>ReCAP re-centers separated normal and abnormal prototypes for each image through a bounded gated modulation.<n>It achieves the best image-level AUROC on all zero-shot and 23 of 24 few-shot settings, and the best zero-shot pixel-level AUROC on all three segmentation datasets.
  arXiv  Detail & Related papers  (2026-08-01T04:46:55Z)
• Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation [3.881211374324378]
  Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.<n>We propose a gradient-free methodology reframing detection from binary classification to an out-of-distribution (OOD) anomaly measurement problem.
  arXiv  Detail & Related papers  (2026-06-03T13:04:23Z)
• Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction [2.201656998025222]
  Metal artifacts from high-attenuation implants severely degrade CT image quality.<n>We propose a paradigm shift: reframing artifact reduction as an in-context reasoning task.<n>Our approach achieves effective artifact suppression with only 16 to 128 paired training examples.
  arXiv  Detail & Related papers  (2026-04-07T14:32:25Z)
• NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting [25.805439969022697]
  We propose NRGS-SLAM, a monocular non-rigid SLAM system for endoscopy based on 3D Gaussian Splatting.<n>We show that NRGS-SLAM achieves more accurate camera pose estimation (up to 50% reduction in RMSE) and higher-quality photo-realistic reconstructions than state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-19T09:03:47Z)
• HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection [10.649984141835189]
  We propose the Hierarchical Adaptation and Alignment Framework (HAAF)<n>At its core is a novel Cross-Level Scaled Alignment mechanism that enforces a sequential calibration order.<n>A dual-branch inference strategy integrates semantic scores with geometric prototypes to ensure stability in few-shot settings.
  arXiv  Detail & Related papers  (2026-01-24T10:31:21Z)
• ColonAdapter: Geometry Estimation Through Foundation Model Adaptation for Colonoscopy [18.844097623387974]
  Estimating 3D geometry from monocular colonoscopy images is challenging due to non-Lambertian surfaces, moving light sources, and large textureless regions.<n>We present ColonAdapter, a self-supervised fine-tuning framework that adapts geometric foundation models for colonoscopy geometry estimation.
  arXiv  Detail & Related papers  (2025-11-27T09:21:11Z)
• Diffusion-Based Data Augmentation for Medical Image Segmentation [2.841725244360927]
  DiffAug is a novel framework that combines textguided diffusion-based generation and automatic segmentation validation.<n>Our framework achieves state-of-the-art performance with 8-10% Dice improvements over baselines.
  arXiv  Detail & Related papers  (2025-08-25T09:49:27Z)
• One-for-More: Continual Diffusion Model for Anomaly Detection [63.50488826645681]
  Anomaly detection methods utilize diffusion models to generate or reconstruct normal samples when given arbitrary anomaly images.<n>Our study found that the diffusion model suffers from severe faithfulness hallucination'' and catastrophic forgetting''<n>We propose a continual diffusion model that uses gradient projection to achieve stable continual learning.
  arXiv  Detail & Related papers  (2025-02-27T07:47:27Z)
• Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection [58.87142367781417]
  A naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked.<n>One potential remedy is incorporating the pre-trained knowledge within the vision foundation models to expand the feature space.<n>By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning fake patterns.
  arXiv  Detail & Related papers  (2024-11-23T19:10:32Z)
• ToDER: Towards Colonoscopy Depth Estimation and Reconstruction with Geometry Constraint Adaptation [67.22294293695255]
  We propose a novel reconstruction pipeline with a bi-directional adaptation architecture named ToDER to get precise depth estimations. Experimental results demonstrate that our approach can precisely predict depth maps in both realistic and synthetic colonoscopy videos.
  arXiv  Detail & Related papers  (2024-07-23T14:24:26Z)
• GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [60.78684630040313]
  Diffusion models tend to reconstruct normal counterparts of test images with certain noises added. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. We propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2024-06-11T17:27:23Z)
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.