edvr_3dconv

EDVR added 3D conv. module

https://github.com/stmrym/edvr_3dconv

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

EDVR added 3D conv. module

Basic Info
  • Host: GitHub
  • Owner: stmrym
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 1.34 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.md

EDVR_3Dconv

EDVR with additional 3D conv. module for synthetic reflection removal.
This repo has been based on EDVR and BasicSR.

Installation

  1. Requirements
  2. Python >= 3.7
  3. PyTorch >= 1.7
  4. NVIDIA GPU + CUDA

  5. Install dependent packages

    bash cd EDVR_3Dconv pip install -r requirements.txt

  6. Install BasicSR

    bash BASICSR_EXT=True python setup.py develop (Details at EDVR and BasicSR Installation)

Datasets

  1. Prepare REDS dataset

    Download REDS dataset and put them in datasets/REDS_dataset/train_shirp.

  2. Create synthetic reflection dataset

    bash python datasets/create_synvideo_train.py python datasets/create_synvideo_val.py python datasets/create_synvideo_test.py

Testing

  1. Configuration

    Edit options/test/EDVR/test_EDVR_M_RR_REDS.yml (Details at Config.md)

  2. Testing

    bash python basicsr/test.py -opt options/test/EDVR/test_EDVR_M_RR_REDS.yml (Details at TrainTest.md)

Training

  1. Configuration

    Edit options/train/EDVR/train_EDVR_M_RR_REDS.yml (Details at Config.md)

  2. Training

    bash python basicsr/train.py -opt options/train/EDVR/train_EDVR_M_RR_REDS.yml (Details at TrainTest.md)

Results

|Input (w/ reflection)| |:---:| || |EDVR| || |EDVR + 3Dconv| ||

License

Apache 2.0 license

Owner

  • Name: SotaMoriyama
  • Login: stmrym
  • Kind: user

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this project, please cite it as below."
title: "BasicSR: Open Source Image and Video Restoration Toolbox"
version: 1.3.5
date-released: 2022-02-16
url: "https://github.com/XPixelGroup/BasicSR"
license: Apache-2.0
authors:
  - family-names: Wang
    given-names: Xintao
  - family-names: Xie
    given-names: Liangbin
  - family-names: Yu
    given-names: Ke
  - family-names: Chan
    given-names: Kelvin C.K.
  - family-names: Loy
    given-names: Chen Change
  - family-names: Dong
    given-names: Chao

GitHub Events

Total
Last Year