Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xiao Feng, Song, Tian Yi, Yao, Jia Wei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908502476193792
author Zhang, Xiao Feng
Song, Tian Yi
Yao, Jia Wei
author_facet Zhang, Xiao Feng
Song, Tian Yi
Yao, Jia Wei
contents Segment Anything (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguishing between shadows and their backgrounds. To address this, we developed Deshadow-Anything, considering the generalization of large-scale datasets, and we performed Fine-tuning on large-scale datasets to achieve image shadow removal. The diffusion model can diffuse along the edges and textures of an image, helping to remove shadows while preserving the details of the image. Furthermore, we design Multi-Self-Attention Guidance (MSAG) and adaptive input perturbation (DDPM-AIP) to accelerate the iterative training speed of diffusion. Experiments on shadow removal tasks demonstrate that these methods can effectively improve image restoration performance.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11715
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal
Zhang, Xiao Feng
Song, Tian Yi
Yao, Jia Wei
Computer Vision and Pattern Recognition
Image and Video Processing
Segment Anything (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguishing between shadows and their backgrounds. To address this, we developed Deshadow-Anything, considering the generalization of large-scale datasets, and we performed Fine-tuning on large-scale datasets to achieve image shadow removal. The diffusion model can diffuse along the edges and textures of an image, helping to remove shadows while preserving the details of the image. Furthermore, we design Multi-Self-Attention Guidance (MSAG) and adaptive input perturbation (DDPM-AIP) to accelerate the iterative training speed of diffusion. Experiments on shadow removal tasks demonstrate that these methods can effectively improve image restoration performance.
title Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2309.11715