computer-vision-5

Single Image Desnowing

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in single-image-desnowing-5

Trend

Dataset

Best Model

Actions

CSD

Libraries

i

Use these libraries to find single-image-desnowing-5 models and implementations

Datasets

CSD

Subtasks

No subtasks available.

Most implemented papers

Restormer: Efficient Transformer for High-Resolution Image Restoration

Salman Hameed Khan, Munawar Hayat, Ming-Hsuan Yang, Syed Waqas Zamir, F. Khan, Aditya Arora•Wed Nov 17 2021

This work proposes an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images.

3334

Content

0

Paper Graph

Simple Baselines for Image Restoration

X. Zhang, Liangyu Chen, Xiaojie Chu, Jian Sun•Sat Apr 09 2022

A simple baseline is proposed that exceeds the SOTA methods and is computationally efficient and reveals that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed.

1273 0

Paper Graph

Uformer: A General U-Shaped Transformer for Image Restoration

Jianmin Bao, Xiaodong Cun, Jianzhuang Liu, Zhendong Wang•Sat Jun 05 2021

Uformer, an effective and efficient Transformer-based architecture for image restoration, in which a hierarchical encoder-decoder network is built using the Transformer block and a learnable multi-scale restoration modulator in the form of a multi- scale spatial bias to adjust features in multiple layers of the Uformer decoder is proposed.

1921 0

Paper Graph

ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss

H. Fang, Cheng-Che Tsai, Wei-Ting Chen, Cheng-Lin Hsieh, I-Hsiang Chen, Jianwei Ding, Sy-Yen Kuo•Thu Sep 30 2021

Snow is a highly complicated atmospheric phenomenon that usually contains snowflake, snow streak, and veiling effect (similar to the haze or the mist). In this literature, we propose a single image desnowing algorithm to address the diversity of snow particles in shape and size. First, to better represent the complex snow shape, we apply the dual-tree wavelet transform and propose a complex wavelet loss in the network. Second, we propose a hierarchical decomposition paradigm in our network for better under-standing the different sizes of snow particles. Last, we propose a novel feature called the contradict channel (CC) for the snow scenes. We find that the regions containing the snow particles tend to have higher intensity in the CC than that in the snow-free regions. We leverage this discriminative feature to construct the contradict channel loss for improving the performance of snow removal. Moreover, due to the limitation of existing snow datasets, to simulate the snow scenarios comprehensively, we propose a large-scale dataset called Comprehensive Snow Dataset (CSD). Experimental results show that the proposed method can favorably outperform existing methods in three synthetic datasets and real-world datasets. The code and dataset are released in https://github.com/weitingchen83/ICCV2021-Single-Image-Desnowing-HDCWNet.

266 0

Paper Graph

TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions

Vishal M. Patel, R. Yasarla, Jeya Maria Jose Valanarasu•Sun Nov 28 2021

This work proposes TransWeather, a transformer-based end-to-end model with just a single encoder and a decoder that can restore an image degraded by any weather condition, which achieves significant improvements across multiple test datasets over both All-in-One network as well as methods fine-tuned for specific tasks.

416 0

Paper Graph

SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing

Sixiang Chen, Tian Ye, Yun Liu, Erkang Chen•Fri Aug 19 2022

A novel transformer, SnowFormer, is proposed, which explores efficient cross-attentions to build local-global context interaction across patches and surpasses existing works that employ local operators or vanilla transformers.

21 0

Paper Graph

Adding a benchmark result helps the community track progress.