paper-with-me

Papers

WavShadow: Wavelet Based Shadow Segmentation and Removal

2024-11-08 · Shreyans Jain, Viraj Vekaria, Karan Gandhi, Aadya Arora

Shadow removal and segmentation remain challenging tasks in computer vision, particularly in complex real world scenarios. This study presents a novel approach that enhances the ShadowFormer model by incorporating Masked Autoencoder (MAE) priors and Fast Fourier Convolution (FFC) blocks, leading to significantly faster convergence and improved performance. We introduce key innovations: (1) integration of MAE priors trained on Places2 dataset for better context understanding, (2) adoption of Haar wavelet features for enhanced edge detection and multiscale analysis, and (3) implementation of a modified SAM Adapter for robust shadow segmentation. Extensive experiments on the challenging DESOBA dataset demonstrate that our approach achieves state of the art results, with notable improvements in both convergence speed and shadow removal quality.

📄 PDF Abstract BibTeX arXiv:2411.05747

Code (0)

등록된 구현이 없습니다.

Tasks

Edge DetectionSegmentationShadow Removal

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
MAE 설명 없음
Adapter 설명 없음
SAM 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors

2025-04-08 · Tao Lin, Qingwang Wang, Qiwei Liang, Minghua Tang 외

Shadow removal is challenging due to the complex interaction of geometry, lighting, and environmental factors. Existing unsupervised methods often overlook shadow-specific priors, leading to incomplete shadow recovery. T…

Shadow Removal

Shadow Removal Refinement via Material-Consistent Shadow Edges

2024-09-10 · Shilin Hu, Hieu Le, ShahRukh Athar, Sagnik Das 외

Shadow boundaries can be confused with material boundaries as both exhibit sharp changes in luminance or contrast within a scene. However, shadows do not modify the intrinsic color or texture of surfaces. Therefore, on b…

Image SegmentationSegmentationSemantic SegmentationShadow Removal

From Shadow Segmentation to Shadow Removal

2020-08-01 · ECCV 2020 8 · Hieu Le, Dimitris Samaras

The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets and hinders the possibility of training large-scale, robust shadow removal algorithms. We propose a shadow…

DiversitySegmentationShadow Removal

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

2023-09-21 · Xiao Feng Zhang, Tian Yi Song, Jia Wei Yao

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 …

Image RestorationImage SegmentationImage Shadow RemovalSegmentation+2

ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer

2024-04-18 · Wei Dong, Han Zhou, Yuqiong Tian, Jingke Sun 외

Shadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and segmentation systems. To effectively elim…

Image Shadow Removalobject-detectionObject DetectionRepresentation Learning+1