NVIDIA's Deep Imagination Team's PyTorch Library
Python
4,078
45 commits
updated Nov 29, 2022
Imaginaire is a pytorch library that contains optimized implementation of several image and video synthesis methods developed at NVIDIA.
Imaginaire is released under NVIDIA Software license. For commercial use, please consult NVIDIA Research Inquiries.
We have a tutorial for each model. Click on the model name, and your browser should take you to the tutorial page for the project.
| Algorithm Name | Feature | Publication |
|---|---|---|
| pix2pixHD | Learn a mapping that converts a semantic image to a high-resolution photorealistic image. | Wang et. al. CVPR 2018 |
| SPADE | Improve pix2pixHD on handling diverse input labels and delivering better output quality. | Park et. al. CVPR 2019 |
| Algorithm Name | Feature | Publication |
|---|---|---|
| UNIT | Learn a one-to-one mapping between two visual domains. | Liu et. al. NeurIPS 2017 |
| MUNIT | Learn a many-to-many mapping between two visual domains. | Huang et. al. ECCV 2018 |
| FUNIT | Learn a style-guided image translation model that can generate translations in unseen domains. | Liu et. al. ICCV 2019 |
| COCO-FUNIT | Improve FUNIT with a content-conditioned style encoding scheme for style code computation. | Saito et. al. ECCV 2020 |
| Algorithm Name | Feature | Publication |
|---|---|---|
| vid2vid | Learn a mapping that converts a semantic video to a photorealistic video. | Wang et. al. NeurIPS 2018 |
| fs-vid2vid | Learn a subject-agnostic mapping that converts a semantic video and an example image to a photoreslitic video. | Wang et. al. NeurIPS 2019 |
| Algorithm Name | Feature | Publication |
|---|---|---|
| wc-vid2vid | Improve vid2vid on view consistency and long-term consistency. | Mallya et. al. ECCV 2020 |
| GANcraft | Convert semantic block worlds to realistic-looking worlds. | Hao et. al. ICCV 2021 |
(top 24 of 31)
4,155 followers · starred Oct 2020
7,036 followers · starred Aug 2021
37 followers · starred Jun 2021
1,108 followers · starred Sep 2020
NVIDIA's Deep Imagination Team's PyTorch Library
Python
4,078
45 commits
updated Nov 29, 2022
Imaginaire is a pytorch library that contains optimized implementation of several image and video synthesis methods developed at NVIDIA.
Imaginaire is released under NVIDIA Software license. For commercial use, please consult NVIDIA Research Inquiries.
We have a tutorial for each model. Click on the model name, and your browser should take you to the tutorial page for the project.
| Algorithm Name | Feature | Publication |
|---|---|---|
| pix2pixHD | Learn a mapping that converts a semantic image to a high-resolution photorealistic image. | Wang et. al. CVPR 2018 |
| SPADE | Improve pix2pixHD on handling diverse input labels and delivering better output quality. | Park et. al. CVPR 2019 |
| Algorithm Name | Feature | Publication |
|---|---|---|
| UNIT | Learn a one-to-one mapping between two visual domains. | Liu et. al. NeurIPS 2017 |
| MUNIT | Learn a many-to-many mapping between two visual domains. | Huang et. al. ECCV 2018 |
| FUNIT | Learn a style-guided image translation model that can generate translations in unseen domains. | Liu et. al. ICCV 2019 |
| COCO-FUNIT | Improve FUNIT with a content-conditioned style encoding scheme for style code computation. | Saito et. al. ECCV 2020 |
| Algorithm Name | Feature | Publication |
|---|---|---|
| vid2vid | Learn a mapping that converts a semantic video to a photorealistic video. | Wang et. al. NeurIPS 2018 |
| fs-vid2vid | Learn a subject-agnostic mapping that converts a semantic video and an example image to a photoreslitic video. | Wang et. al. NeurIPS 2019 |
| Algorithm Name | Feature | Publication |
|---|---|---|
| wc-vid2vid | Improve vid2vid on view consistency and long-term consistency. | Mallya et. al. ECCV 2020 |
| GANcraft | Convert semantic block worlds to realistic-looking worlds. | Hao et. al. ICCV 2021 |
(top 24 of 31)
4,155 followers · starred Oct 2020
7,036 followers · starred Aug 2021
37 followers · starred Jun 2021
1,108 followers · starred Sep 2020
