Saved in:
Bibliographic Details
Main Authors: Chen, Bohao, Zhang, Yanchao, Lv, Yanan, Han, Hua, Chen, Xi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.16792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910714152615936
author Chen, Bohao
Zhang, Yanchao
Lv, Yanan
Han, Hua
Chen, Xi
author_facet Chen, Bohao
Zhang, Yanchao
Lv, Yanan
Han, Hua
Chen, Xi
contents Diffusion models have recently emerged as a powerful technique in image generation, especially for image super-resolution tasks. While 2D diffusion models significantly enhance the resolution of individual images, existing diffusion-based methods for 3D volume super-resolution often struggle with structure discontinuities in axial direction and high sampling costs. In this work, we present a novel approach that leverages the 2D diffusion model and lateral continuity within the volume to enhance 3D volume electron microscopy (vEM) super-resolution. We first simulate lateral degradation with slices in the XY plane and train a 2D diffusion model to learn how to restore the degraded slices. The model is then applied slice-by-slice in the lateral direction of low-resolution volume, recovering slices while preserving inherent lateral continuity. Following this, a high-frequency-aware 3D super-resolution network is trained on the recovery lateral slice sequences to learn spatial feature transformation across slices. Finally, the network is applied to infer high-resolution volumes in the axial direction, enabling 3D super-resolution. We validate our approach through comprehensive evaluations, including image similarity assessments, resolution analysis, and performance on downstream tasks. Our results on two publicly available focused ion beam scanning electron microscopy (FIB-SEM) datasets demonstrate the robustness and practical applicability of our framework for 3D volume super-resolution.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16792
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Diffusion to Resolution: Leveraging 2D Diffusion Models for 3D Super-Resolution Task
Chen, Bohao
Zhang, Yanchao
Lv, Yanan
Han, Hua
Chen, Xi
Computer Vision and Pattern Recognition
Diffusion models have recently emerged as a powerful technique in image generation, especially for image super-resolution tasks. While 2D diffusion models significantly enhance the resolution of individual images, existing diffusion-based methods for 3D volume super-resolution often struggle with structure discontinuities in axial direction and high sampling costs. In this work, we present a novel approach that leverages the 2D diffusion model and lateral continuity within the volume to enhance 3D volume electron microscopy (vEM) super-resolution. We first simulate lateral degradation with slices in the XY plane and train a 2D diffusion model to learn how to restore the degraded slices. The model is then applied slice-by-slice in the lateral direction of low-resolution volume, recovering slices while preserving inherent lateral continuity. Following this, a high-frequency-aware 3D super-resolution network is trained on the recovery lateral slice sequences to learn spatial feature transformation across slices. Finally, the network is applied to infer high-resolution volumes in the axial direction, enabling 3D super-resolution. We validate our approach through comprehensive evaluations, including image similarity assessments, resolution analysis, and performance on downstream tasks. Our results on two publicly available focused ion beam scanning electron microscopy (FIB-SEM) datasets demonstrate the robustness and practical applicability of our framework for 3D volume super-resolution.
title From Diffusion to Resolution: Leveraging 2D Diffusion Models for 3D Super-Resolution Task
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.16792