We lifted 12 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| microsoft/DisentangledFaceGAN | canonical | 0 of 10 |
| microsoft/DiscoFaceGAN | pwc_unofficial | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| tuple_product | Ran | microsoft/DiscoFaceGAN/dnnlib/util.py code served (permissive licence) · get_code("efd5d4ab788539f4") |
| CoeffDecoder | Not yet run | microsoft/DisentangledFaceGAN/generate_images.py code served (permissive licence) · get_code("b841315157ec8c2b") |
| FaceParser | Not yet run | microsoft/DisentangledFaceGAN/training/networks_parser.py code served (permissive licence) · get_code("e2e11f3a3cab6434") |
| G_wgan | Not yet run | microsoft/DisentangledFaceGAN/training/loss.py code served (permissive licence) · get_code("07f42dc7a77da207") |
| MaskNet | Not yet run | microsoft/DisentangledFaceGAN/training/networks_parser.py code served (permissive licence) · get_code("44b7510fbf57e6c6") |
| ask_yes_no | Not yet run | microsoft/DisentangledFaceGAN/dnnlib/util.py code served (permissive licence) · get_code("9d31d2c4cd16bb2d") |
| execute_cmdline | Not yet run | microsoft/DiscoFaceGAN/dataset_tool.py code served (permissive licence) · get_code("31857d2f579c1600") |
| format_time | Not yet run | microsoft/DisentangledFaceGAN/dnnlib/util.py code served (permissive licence) · get_code("053fc534bc6bb989") |
| fpn | Not yet run | microsoft/DisentangledFaceGAN/training/networks_parser.py code served (permissive licence) · get_code("4192aa298eb02e26") |
| gaussian_blur | Not yet run | microsoft/DisentangledFaceGAN/training/loss_control.py code served (permissive licence) · get_code("00e0c8745f3f99e9") |
| gaussian_kernel | Not yet run | microsoft/DisentangledFaceGAN/training/loss_control.py code served (permissive licence) · get_code("66f866bbf81a287d") |
| z_to_lambda_mapping | Not yet run | microsoft/DisentangledFaceGAN/generate_images.py code served (permissive licence) · get_code("50b51702f15ad7d4") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors into adversarial learning and train the network to imitate the image formation of an analytic 3D face deformation and rendering process. To deal with the generation freedom induced by the domain gap between real and rendered faces, we further introduce contrastive learning to promote disentanglement by comparing pairs of generated images. Experiments show that through our imitative-contrastive learning, the factor variations are very well disentangled and the properties of a generated face can be precisely controlled. We also analyze the learned latent space and present several meaningful properties supporting factor disentanglement. Our method can also be used to embed real images into the disentangled latent space. We hope our method could provide new understandings of the relationship between physical properties and deep image synthesis.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.11660")
get_code_for_paper("2004.11660")
have("2004.11660")
Connect an agent — have() is free.