Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2411.05747 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917834388406272 |
|---|---|
| author | Jain, Shreyans Vekaria, Viraj Gandhi, Karan Arora, Aadya |
| author_facet | Jain, Shreyans Vekaria, Viraj Gandhi, Karan Arora, Aadya |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05747 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WavShadow: Wavelet Based Shadow Segmentation and Removal Jain, Shreyans Vekaria, Viraj Gandhi, Karan Arora, Aadya Computer Vision and Pattern Recognition 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. |
| title | WavShadow: Wavelet Based Shadow Segmentation and Removal |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.05747 |