LANet

Our work proposes an adaptive learning attention network (LANet) to solve the problem of color casts and low illumination in underwater images.

Dependencies

The code runs with Python=3.6 and requires Pytorch of version 1.7 or higher. Please pip install the following packages:

numpy=1.20.2
torchvision=0.8.0
matplotlib=3.4.2
opencv-python=4.5.2.54
scipy=1.7.0

Training

1. Download the code
2. run Python train.py --input_images-path ./data/trainA/ --label_images_path ./data/trainB/ 
3. Find checkpoint in the "./checkpoints/" folder
The training data includes input data and label data. input data are in the "./data/trainA" folder, label data are in the "./data/trainB" folder

Testing

1. pre-trained models in the "./checkpoints/" folder
2. Put your testing images in the "./data/test/" folder 
3. run Python test.py --test_pth ./data/test/ --snapshot_pth ./checkpoints/model_epoch_40.pk
4. Find the result in "./results" folder

Contact

If you have any questions, please contact Shiben Liu at [email protected].

Underwater image enhancement

Related tags

Overview

LANet

Dependencies

Training

Testing

Contact

Owner

LiuShiBen

PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

RGB-stacking 🛑 🟩 🔷 for robotic manipulation

[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465

dualFace: Two-Stage Drawing Guidance for Freehand Portrait Sketching (CVMJ)

[CVPR 2021] Teachers Do More Than Teach: Compressing Image-to-Image Models (CAT)

This is the implementation of our work Deep Extreme Cut (DEXTR), for object segmentation from extreme points.

Learning Generative Models of Textured 3D Meshes from Real-World Images, ICCV 2021

Hso-groupie - A pwnable challenge in Real World CTF 4th

ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

git《Beta R-CNN: Looking into Pedestrian Detection from Another Perspective》(NeurIPS 2020) GitHub:[fig3]

[CVPR2021] DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets

ML-Decoder: Scalable and Versatile Classification Head

A Survey on Deep Learning Technique for Video Segmentation

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

Video Corpus Moment Retrieval with Contrastive Learning (SIGIR 2021)

An implementation of Deep Forest 2021.2.1.

Deep Dual Consecutive Network for Human Pose Estimation (CVPR2021)

PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper "Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations" [arXiv 2022].