Note

You are reading the documentation for MMEditing 0.x, which will soon be deprecated by the end of 2022. We recommend you upgrade to MMEditing 1.0 to enjoy fruitful new features and better performance brought by OpenMMLab 2.0. Check out the changelog, code and documentation of MMEditing 1.0 for more details.

Overview

• Number of checkpoints: 80

• Number of configs: 71

• Number of papers: 28

  • ALGORITHM: 28

For supported datasets, see datasets overview.

Inpainting Models

• Number of checkpoints: 8

• Number of configs: 9

• Number of papers: 5

  • [ALGORITHM] Aggregated Contextual Transformations for High-Resolution Image Inpainting (⇨)

  • [ALGORITHM] Free-Form Image Inpainting With Gated Convolution (⇨)

  • [ALGORITHM] Generative Image Inpainting With Contextual Attention (⇨)

  • [ALGORITHM] Globally and Locally Consistent Image Completion (⇨)

  • [ALGORITHM] Image Inpainting for Irregular Holes Using Partial Convolutions (⇨)

Matting Models

• Number of checkpoints: 9

• Number of configs: 9

• Number of papers: 3

  • [ALGORITHM] Deep Image Matting (⇨)

  • [ALGORITHM] Indices Matter: Learning to Index for Deep Image Matting (⇨)

  • [ALGORITHM] Natural Image Matting via Guided Contextual Attention (⇨)

Super-Resolution Models

• Number of checkpoints: 46

• Number of configs: 40

• Number of papers: 16

  • [ALGORITHM] Basicvsr: The Search for Essential Components in Video Super-Resolution and Beyond (⇨ ⇨)

  • [ALGORITHM] Basicvsr++: Improving Video Super-Resolution With Enhanced Propagation and Alignment (⇨)

  • [ALGORITHM] Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation (⇨)

  • [ALGORITHM] Edvr: Video Restoration With Enhanced Deformable Convolutional Networks (⇨)

  • [ALGORITHM] Enhanced Deep Residual Networks for Single Image Super-Resolution (⇨)

  • [ALGORITHM] Esrgan: Enhanced Super-Resolution Generative Adversarial Networks (⇨)

  • [ALGORITHM] Glean: Generative Latent Bank for Large-Factor Image Super-Resolution (⇨)

  • [ALGORITHM] Image Super-Resolution Using Deep Convolutional Networks (⇨)

  • [ALGORITHM] Learning Continuous Image Representation With Local Implicit Image Function (⇨)

  • [ALGORITHM] Learning Texture Transformer Network for Image Super-Resolution (⇨)

  • [ALGORITHM] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (⇨)

  • [ALGORITHM] Real-Esrgan: Training Real-World Blind Super-Resolution With Pure Synthetic Data (⇨)

  • [ALGORITHM] Realbasicvsr: Investigating Tradeoffs in Real-World Video Super-Resolution (⇨)

  • [ALGORITHM] Residual Dense Network for Image Super-Resolution (⇨)

  • [ALGORITHM] Tdan: Temporally-Deformable Alignment Network for Video Super-Resolution (⇨)

  • [ALGORITHM] Video Enhancement With Task-Oriented Flow (⇨)

Generation Models

• Number of checkpoints: 10

• Number of configs: 10

• Number of papers: 2

  • [ALGORITHM] Image-to-Image Translation With Conditional Adversarial Networks (⇨)

  • [ALGORITHM] Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks (⇨)

Frame-Interpolation Models

• Number of checkpoints: 7

• Number of configs: 3

• Number of papers: 3

  • [ALGORITHM] Channel Attention Is All You Need for Video Frame Interpolation (⇨)

  • [ALGORITHM] Flavr: Flow-Agnostic Video Representations for Fast Frame Interpolation (⇨)

  • [ALGORITHM] Video Enhancement With Task-Oriented Flow (⇨)