SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10257 · ECCV · 2022

Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis

Jeong-Gi Kwak, Yuanming Li, Dongsik Yoon, Donghyeon Kim, David Han, Hanseok Ko

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 5 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.

RepositoryRoleRan
jgkwak95/SURF-GAN — 5 of 9
FunctionStatusWhere it lives
Sine Ran jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("9adcf0dd8a6b1ea0")
SinedLayer_noise Ran jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("4d45205e98b68220")
SubspaceLayer Ran jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("e5faf4e6af78cdc1")
UniformBoxWarp Ran jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("1d55443a90437b04")
frequency_init Ran jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("579255f1d41bda52")
ImplicitGenerator3d_SURF Not yet run jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("bdc0a31c438a4ad8")
SURFBlock Not yet run jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("6623039f97a9d00b")
SURFSIREN Not yet run jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("a54a523697ab7d47")
first_layer_film_sine_init Not yet run jgkwak95/SURF-GAN/generators/generator_surf.py
code served (permissive licence) · get_code("1542a53b3eb3b17d")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Over the years, 2D GANs have achieved great successes in photorealistic portrait generation. However, they lack 3D understanding in the generation process, thus they suffer from multi-view inconsistency problem. To alleviate the issue, many 3D-aware GANs have been proposed and shown notable results, but 3D GANs struggle with editing semantic attributes. The controllability and interpretability of 3D GANs have not been much explored. In this work, we propose two solutions to overcome these weaknesses of 2D GANs and 3D-aware GANs. We first introduce a novel 3D-aware GAN, SURF-GAN, which is capable of discovering semantic attributes during training and controlling them in an unsupervised manner. After that, we inject the prior of SURF-GAN into StyleGAN to obtain a high-fidelity 3D-controllable generator. Unlike existing latent-based methods allowing implicit pose control, the proposed 3D-controllable StyleGAN enables explicit pose control over portrait generation. This distillation allows direct compatibility between 3D control and many StyleGAN-based techniques (e.g., inversion and stylization), and also brings an advantage in terms of computational resources. Our codes are available at https://github.com/jgkwak95/SURF-GAN.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.10257")
get_code_for_paper("2207.10257")
have("2207.10257")

Connect an agent — have() is free.