DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity

• URL: http://arxiv.org/abs/2211.08089v4
• Date: Sun, 14 Apr 2024 13:02:59 GMT
• Title: DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
• Authors: Yeying Jin, Wei Ye, Wenhan Yang, Yuan Yuan, Robby T. Tan,
• Abstract summary: We present a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets.
• Score: 54.831083157152136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Removing soft and self shadows that lack clear boundaries from a single image is still challenging. Self shadows are shadows that are cast on the object itself. Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows. In this paper, we present DeS3, a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our novel ViT similarity loss utilizes features extracted from a pre-trained Vision Transformer. This loss helps guide the reverse sampling towards recovering scene structures. Our adaptive attention is able to differentiate shadow regions from the underlying objects, as well as shadow regions from the object casting the shadow. This capability enables DeS3 to better recover the structures of objects even when they are partially occluded by shadows. Different from existing methods that rely on constraints during the training phase, we incorporate the ViT similarity during the sampling stage. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets, removing hard, soft, and self shadows robustly. Specifically, our method outperforms the SOTA method by 16\% of the RMSE of the whole image on the LRSS dataset. Our data and code is available at: \url{https://github.com/jinyeying/DeS3_Deshadow}

Related papers

• Shadow Removal Refinement via Material-Consistent Shadow Edges [33.8383848078524]
  On both sides of shadow edges traversing regions with the same material, the original color and textures should be the same if the shadow is removed properly. We fine-tune SAM, an image segmentation foundation model, to produce a shadow-invariant segmentation and then extract material-consistent shadow edges. We demonstrate the effectiveness of our method in improving shadow removal results on more challenging, in-the-wild images.
  arXiv  Detail & Related papers  (2024-09-10T20:16:28Z)
• Progressive Recurrent Network for Shadow Removal [99.1928825224358]
  Single-image shadow removal is a significant task that is still unresolved. Most existing deep learning-based approaches attempt to remove the shadow directly, which can not deal with the shadow well. We propose a simple but effective Progressive Recurrent Network (PRNet) to remove the shadow progressively.
  arXiv  Detail & Related papers  (2023-11-01T11:42:45Z)
• Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal [19.391619888009064]
  State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs. We find that two tasks exhibit poor compatibility, and using shared weights for these two tasks could lead to the model being optimized towards only one task. We propose to handle these two tasks separately and leverage the identical mapping results to guide the shadow restoration in an iterative manner.
  arXiv  Detail & Related papers  (2023-05-18T01:36:23Z)
• Structure-Informed Shadow Removal Networks [67.57092870994029]
  Existing deep learning-based shadow removal methods still produce images with shadow remnants. We propose a novel structure-informed shadow removal network (StructNet) to leverage the image-structure information to address the shadow remnant problem. Our method outperforms existing shadow removal methods, and our StructNet can be integrated with existing methods to improve them further.
  arXiv  Detail & Related papers  (2023-01-09T06:31:52Z)
• Shadow Removal by High-Quality Shadow Synthesis [78.56549207362863]
  HQSS employs a shadow feature encoder and a generator to synthesize pseudo images. HQSS is observed to outperform the state-of-the-art methods on ISTD dataset, Video Shadow Removal dataset, and SRD dataset.
  arXiv  Detail & Related papers  (2022-12-08T06:52:52Z)
• DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network [28.6541488555978]
  We propose an unsupervised domain-classifier guided shadow removal network, DC-ShadowNet. We introduce novel losses based on physics-based shadow-free chromaticity, shadow-robust perceptual features, and boundary smoothness. Our experiments show that all these novel components allow our method to handle soft shadows, and also to perform better on hard shadows.
  arXiv  Detail & Related papers  (2022-07-21T12:04:16Z)
• Shadow-Aware Dynamic Convolution for Shadow Removal [80.82708225269684]
  We introduce a novel Shadow-Aware Dynamic Convolution (SADC) module to decouple the interdependence between the shadow region and the non-shadow region. Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module. We develop a novel intra-convolution distillation loss to strengthen the information flow from the non-shadow region to the shadow region.
  arXiv  Detail & Related papers  (2022-05-10T14:00:48Z)
• R2D: Learning Shadow Removal to Enhance Fine-Context Shadow Detection [64.10636296274168]
  Current shadow detection methods perform poorly when detecting shadow regions that are small, unclear or have blurry edges. We propose a new method called Restore to Detect (R2D), where a deep neural network is trained for restoration (shadow removal) We show that our proposed method R2D improves the shadow detection performance while being able to detect fine context better compared to the other recent methods.
  arXiv  Detail & Related papers  (2021-09-20T15:09:22Z)
• Physics-based Shadow Image Decomposition for Shadow Removal [36.41558227710456]
  We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image. We train and test our framework on the most challenging shadow removal dataset.
  arXiv  Detail & Related papers  (2020-12-23T23:06:38Z)
• From Shadow Segmentation to Shadow Removal [34.762493656937366]
  The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets. We propose a shadow removal method that can be trained using only shadow and non-shadow patches cropped from the shadow images themselves.
  arXiv  Detail & Related papers  (2020-08-01T14:00:10Z)

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.