Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Doc] Update model zoo for documents #400

Merged
merged 5 commits into from
Jul 1, 2021
Merged

[Doc] Update model zoo for documents #400

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
beb85ec
Update model zoo for documents
ckkelvinchan Jun 29, 2021
9e60dce
Collapse instructions
innerlee Jul 1, 2021
ce350c7
bold them
innerlee Jul 1, 2021
73024b5
hr br
innerlee Jul 1, 2021
1bb2b3a
cool
innerlee Jul 1, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions configs/inpainting/deepfillv1/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,10 @@
# Generative Image Inpainting with Contextual Attention

## Introduction
# DeepFillv1 (CVPR'2018)

<!-- [ALGORITHM] -->

<details>
<summary align="right">DeepFillv1 (CVPR'2018)</summary>

```bibtex
@inproceedings{yu2018generative,
title={Generative image inpainting with contextual attention},
Expand All @@ -14,15 +15,17 @@
}
```

## Results and models
</details>

<br/>

### Places365-Challenge
**Places365-Challenge**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :--------------------------------------------------------------------------: | :---------: | :--------: | :---------: | :-----------: | :------: | :----: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [DeepFillv1](/configs/inpainting/deepfillv1/deepfillv1_256x256_8x2_places.py) | square bbox | 256x256 | 3500k | Places365-val | 11.019 | 23.429 | 0.862 | [model](https://download.openmmlab.com/mmediting/inpainting/deepfillv1/deepfillv1_256x256_8x2_places_20200619-c00a0e21.pth) \| [log](https://download.openmmlab.com/mmediting/inpainting/deepfillv1/deepfillv1_256x256_8x2_places_20200619-c00a0e21.log.json) |

### CelebA-HQ
**CelebA-HQ**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :--------------------------------------------------------------------------: | :---------: | :--------: | :---------: | :--------: | :------: | :----: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
14 changes: 8 additions & 6 deletions configs/inpainting/deepfillv2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Free-form Image Inpainting with Gated Convolution

## Introduction
# DeepFillv2 (CVPR'2019)

<!-- [ALGORITHM] -->
<details>
<summary align="right">DeepFillv2 (CVPR'2019)</summary>

```bibtex
@inproceedings{yu2019free,
Expand All @@ -14,15 +14,17 @@
}
```

## Results and models
</details>

<br/>

### Places365-Challenge
**Places365-Challenge**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :--------------------------------------------------------------------------: | :-------: | :--------: | :---------: | :-----------: | :------: | :----: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [DeepFillv2](/configs/inpainting/deepfillv2/deepfillv2_256x256_8x2_places.py) | free-form | 256x256 | 100k | Places365-val | 8.635 | 22.398 | 0.815 | [model](https://download.openmmlab.com/mmediting/inpainting/deepfillv2/deepfillv2_256x256_8x2_places_20200619-10d15793.pth) \| [log](https://download.openmmlab.com/mmediting/inpainting/deepfillv2/deepfillv2_256x256_8x2_places_20200619-10d15793.log.json) |

### CelebA-HQ
**CelebA-HQ**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :--------------------------------------------------------------------------: | :-------: | :--------: | :---------: | :--------: | :------: | :----: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
16 changes: 9 additions & 7 deletions configs/inpainting/global_local/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Globally and Locally Consistent Image Completion

## Introduction
# Global&Local (ToG'2017)

<!-- [ALGORITHM] -->
<details>
<summary align="right">Global&Local (ToG'2017)</summary>

```bibtex
@article{iizuka2017globally,
Expand All @@ -17,17 +17,19 @@
}
```

*Note that we do not apply the post-processing module in Global&Local for a fair comparison with current deep inpainting methods.*
</details>

## Results and models
<br/>

*Note that we do not apply the post-processing module in Global&Local for a fair comparison with current deep inpainting methods.*

### Places365-Challenge
**Places365-Challenge**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :-----------------------------------------------------------------------: | :---------: | :--------: | :---------: | :-----------: | :------: | :----: | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [Global&Local](/configs/inpainting/global_local/gl_256x256_8x12_places.py) | square bbox | 256x256 | 500k | Places365-val | 11.164 | 23.152 | 0.862 | [model](https://download.openmmlab.com/mmediting/inpainting/global_local/gl_256x256_8x12_places_20200619-52a040a8.pth) \| [log](https://download.openmmlab.com/mmediting/inpainting/global_local/gl_256x256_8x12_places_20200619-52a040a8.log.json) |

### CelebA-HQ
**CelebA-HQ**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :-----------------------------------------------------------------------: | :---------: | :--------: | :---------: | :--------: | :------: | :----: | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
15 changes: 9 additions & 6 deletions configs/inpainting/partial_conv/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,10 @@
# Image inpainting for Irregular Holes using Partial Convolutions

## Introduction
# PConv (ECCV'2018)

<!-- [ALGORITHM] -->

<details>
<summary align="right">PConv (ECCV'2018)</summary>

```bibtex
@inproceedings{liu2018image,
title={Image inpainting for irregular holes using partial convolutions},
Expand All @@ -14,15 +15,17 @@
}
```

## Results and models
</details>

<br/>

### Places365-Challenge
**Places365-Challenge**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :-------------------------------------------------------------------------: | :-------: | :--------: | :---------: | :-----------: | :------: | :----: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| [PConv](/configs/inpainting/partial_conv/pconv_256x256_stage2_4x2_places.py) | free-form | 256x256 | 500k | Places365-val | 8.776 | 22.762 | 0.801 | [model](https://download.openmmlab.com/mmediting/inpainting/pconv/pconv_256x256_stage2_4x2_places_20200619-1ffed0e8.pth) \| [log](https://download.openmmlab.com/mmediting/inpainting/pconv/pconv_256x256_stage2_4x2_places_20200619-1ffed0e8.log.json) |

### CelebA-HQ
**CelebA-HQ**

| Method | Mask Type | Resolution | Train Iters | Test Set | l1 error | PSNR | SSIM | Download |
| :-------------------------------------------------------------------------: | :-------: | :--------: | :---------: | :--------: | :------: | :----: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
10 changes: 6 additions & 4 deletions configs/mattors/dim/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Deep Image Matting

## Introduction
# DIM (CVPR'2017)

<!-- [ALGORITHM] -->
<details>
<summary align="right">DIM (CVPR'2017)</summary>

```bibtex
@inproceedings{xu2017deep,
Expand All @@ -14,7 +14,9 @@
}
```

## Results and Models
</details>

<br/>

| Method | SAD | MSE | GRAD | CONN | Download |
| :------------------------------------------------------------------------: | :------: | :-------: | :------: | :------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
12 changes: 7 additions & 5 deletions configs/mattors/gca/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Natural Image Matting via Guided Contextual Attention

## Introduction
# GCA (AAAI'2020)

<!-- [ALGORITHM] -->
<details>
<summary align="right">GCA (AAAI'2020)</summary>

```bibtex
@inproceedings{li2020natural,
Expand All @@ -13,7 +13,9 @@
}
```

## Results and Models
</details>

<br/>

| Method | SAD | MSE | GRAD | CONN | Download |
| :--------------------------------------------------------------------: | :-------: | :--------: | :-------: | :-------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand All @@ -22,7 +24,7 @@
| [baseline (our)](/configs/mattors/gca/baseline_r34_4x10_200k_comp1k.py) | 36.50 | 0.0090 | 17.40 | 34.33 | [model](https://download.openmmlab.com/mmediting/mattors/gca/baseline_r34_4x10_200k_comp1k_SAD-36.50_20200614_105701-95be1750.pth) \| [log](https://download.openmmlab.com/mmediting/mattors/gca/baseline_r34_4x10_200k_comp1k_20200614_105701.log.json) |
| [GCA (our)](/configs/mattors/gca/gca_r34_4x10_200k_comp1k.py) | **34.77** | **0.0080** | **16.33** | **32.20** | [model](https://download.openmmlab.com/mmediting/mattors/gca/gca_r34_4x10_200k_comp1k_SAD-34.77_20200604_213848-4369bea0.pth) \| [log](https://download.openmmlab.com/mmediting/mattors/gca/gca_r34_4x10_200k_comp1k_20200604_213848.log.json) |

### More results
**More results**

| Method | SAD | MSE | GRAD | CONN | Download |
| :-----------------------------------------------------------------------------------------: | :---: | :----: | :---: | :---: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
12 changes: 7 additions & 5 deletions configs/mattors/indexnet/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Indices Matter: Learning to Index for Deep Image Matting

## Introduction
# IndexNet (ICCV'2019)

<!-- [ALGORITHM] -->
<details>
<summary align="right">IndexNet (ICCV'2019)</summary>

```bibtex
@inproceedings{hao2019indexnet,
Expand All @@ -13,7 +13,9 @@
}
```

## Results and Models
</details>

<br/>

| Method | SAD | MSE | GRAD | CONN | Download |
| :--------------------------------------------------------------------------: | :------: | :-------: | :------: | :------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand All @@ -22,7 +24,7 @@

> The performance of training (best performance) with different random seeds diverges in a large range. You may need to run several experiments for each setting to obtain the above performance.

### More result
**More result**

| Method | SAD | MSE | GRAD | CONN | Download |
| :-----------------------------------------------------------------------------------------------: | :---: | :---: | :---: | :---: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
15 changes: 8 additions & 7 deletions configs/restorers/basicvsr/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
# BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond

## Introduction
# BasicVSR (CVPR'2021)

<!-- [ALGORITHM] -->

```
<details>
<summary align="right">BasicVSR (CVPR'2021)</summary>

```bibtex
@InProceedings{chan2021basicvsr,
author = {Chan, Kelvin CK and Wang, Xintao and Yu, Ke and Dong, Chao and Loy, Chen Change},
title = {BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond},
Expand All @@ -13,13 +14,13 @@
}
```

## Results and Models
</details>

Evaluated on RGB channels for REDS4 and Y channel for others. The metrics are `PSNR`/`SSIM`.
<br/>

Evaluated on RGB channels for REDS4 and Y channel for others. The metrics are `PSNR` / `SSIM` .
The pretrained weights of SPyNet can be found [here](https://download.openmmlab.com/mmediting/restorers/basicvsr/spynet_20210409-c6c1bd09.pth).


| Method | REDS4 (BIx4)<br>PSNR/SSIM (RGB) | Vimeo-90K-T (BIx4)<br>PSNR/SSIM (Y) | Vid4 (BIx4)<br>PSNR/SSIM (Y) | UDM10 (BDx4)<br>PSNR/SSIM (Y) | Vimeo-90K-T (BDx4)<br>PSNR/SSIM (Y) | Vid4 (BDx4)<br>PSNR/SSIM (Y) | Download |
|:------------------------------------------------------------------------------------------------------------------------------:|:-------------------------------:|:-----------------------------------:|:----------------------------:|:-----------------------------:|:-----------------------------------:|:----------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| [basicvsr_reds4](https://github.com/open-mmlab/mmediting/blob/master/configs/restorers/basicvsr/basicvsr_reds4.py) | **31.4170/0.8909** | 36.2848/0.9395 | 27.2694/0.8318 | 33.4478/0.9306 | 34.4700/0.9286 | 24.4541/0.7455 | [model](https://download.openmmlab.com/mmediting/restorers/basicvsr/basicvsr_reds4_20120409-0e599677.pth) \| [log](https://download.openmmlab.com/mmediting/restorers/basicvsr/basicvsr_reds4_20210409_092646.log.json) |
Expand Down
14 changes: 8 additions & 6 deletions configs/restorers/dic/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
# Learning Texture Transformer Network for Image Super-Resolution

## Introduction
# DIC (CVPR'2020)

<!-- [ALGORITHM] -->
<details>

<summary align="right">DIC (CVPR'2020)</summary>

```bibtex
@inproceedings{ma2020deep,
Expand All @@ -14,11 +15,12 @@
}
```

## Results
</details>

Evaluated on RGB channels, `scale` pixels in each border are cropped before evaluation.
<br/>

The metrics are `PSNR / SSIM`.
Evaluated on RGB channels, `scale` pixels in each border are cropped before evaluation.
The metrics are `PSNR / SSIM` .

| Method | scale | CUFED | Download |
| :------------------------------------------------------------------------------------: | :---: | :--------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
Expand Down
Loading