guolanqing / awesome-shadow-removal Goto Github PK
View Code? Open in Web Editor NEWCollection of recent shadow removal works, including papers, codes, datasets, and metrics.
Collection of recent shadow removal works, including papers, codes, datasets, and metrics.
There are still many papers that have not been included
ACM MM 2023 FSR-Net: Deep Fourier Network for Shadow Removal
ICCV 2023 Leveraging Inpainting for Single-Image Shadow Removal
WACV2024 Latent Feature-Guided Diffusion Models for Shadow Removal
AAAI2024 DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
arXiv2023 Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal
Supervised learning:
CVPR 18: Direction-Aware Spatial Context Features for Shadow Detection
ECCV18:Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
TIP 21: Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
Dataset:
CUHKShadow: https://github.com/xw-hu/CUHK-Shadow#cuhk-shadow-dateset
Instance Shadow Detection:
CVPR 20: Instance Shadow Detection
CVPR 21: Single-Stage Instance Shadow Detection with Bidirectional Relation Learning
TPAMI 23: Instance Shadow Detection with A Single-Stage Detector
Arxiv 22: Video Instance Shadow Detection
Portrait Shadow:
SIGGRAPH 20: Portrait Shadow Manipulation
TIP2023 Structure-Informed Shadow Removal Networks
PG2022 Depth‐Aware-Shadow-Removal
PG2023 Facial Image Shadow Removal via Graph-based Feature Fusion
ACMMM2023 Exploiting Residual and Illumination with GANs for Shadow Detection and Shadow Removal
CVPR2022 Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training
WACV2023 Fine-Context Shadow Detection Using Shadow Removal
CVPR2023 SCOTCH and SODA: A Transformer Video Shadow Detection Framework
ICCV2023 Adaptive Illumination Mapping for Shadow Detection in Raw Images
ICCV2023 SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels
ICCV2023 High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net
CVPR2023 Document Image Shadow Removal Guided by Color-Aware Background
ICASSP2024 SHADOCFORMER: A SHADOW-ATTENTIVE THRESHOLD DETECTOR WITH
CASCADED FUSION REFINER FOR DOCUMENT SHADOW REMOVAL
ICASSP2023 LP-IOANET: EFFICIENT HIGH RESOLUTION DOCUMENT SHADOW REMOVAL
ICASSP2023 Shadocnet: Learning spatial-aware tokens in transformer for document shadow removal
Can I participate in the cooperation of this Github repository? I would also like to add some work to this repository
ICCV 2023: SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels (A refined SBU test set)
TIP 2021: Revisiting Shadow Detection: A New Benchmark Dataset for Complex World (A complex shadow detection dataset: CUHKShadow)
Is there a shadow removal dataset for complex traffic scenarios? I only found the shadow detection data set about KITTI data set collected in CUHK data. This data set only has shadow image and shadow mask, but no GT image without shadow is provided. Would you like to ask me how to use this data set to achieve shadow removal?
Dear author, thanks for sharing the great works! I have a use case where the shadow is extremely dark, i.e. basically nothing can be seen in the shadow. Any work have been done on this kind of dark shadow? Is it more like an image inpainting or image generation task, rather than shadow removal task? Most shadow removal projects seem to remove a layer of shadow but the texture underneath is still expected? Thank you very much!
I found that the SRD Dataset can be downloaded from either the first author's website or the last author's website. I would like to request a correction to the repository.
https://github.com/Liangqiong/DeShadowNet
https://www.cs.cityu.edu.hk/~rynson/publications.html
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.