We lifted 10 functions out of this paper's own repositories and ran 6 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 |
|---|---|---|
| PeterouZh/CIPS-3D | canonical | 6 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| create_samples | Ran | PeterouZh/CIPS-3D/piGAN_lib/extract_shapes.py code served (permissive licence) · get_code("306b4b17e95e50e5") |
| get_current_step | Ran | PeterouZh/CIPS-3D/piGAN_lib/curriculums.py code served (permissive licence) · get_code("a551faf28fc86a9f") |
| last_upsample_step | Ran | PeterouZh/CIPS-3D/piGAN_lib/curriculums.py code served (permissive licence) · get_code("31312e8e88c4d95c") |
| next_upsample_step | Ran | PeterouZh/CIPS-3D/piGAN_lib/curriculums.py code served (permissive licence) · get_code("738ade559b76771c") |
| parser_args_from_list | Ran | PeterouZh/CIPS-3D/bash/modelarts/start_modelarts_v2.py code served (permissive licence) · get_code("24cae30ebed85892") |
| tensor_to_PIL | Ran | PeterouZh/CIPS-3D/piGAN_lib/inverse_render.py code served (permissive licence) · get_code("ba5ab942e8001328") |
| generate_img | Not yet run | PeterouZh/CIPS-3D/piGAN_lib/render_multiview_images.py code served (permissive licence) · get_code("397ffed73d1069ee") |
| get_dataset | Not yet run | PeterouZh/CIPS-3D/piGAN_lib/datasets.py code served (permissive licence) · get_code("5d4213f664c985e6") |
| get_dataset_distributed | Not yet run | PeterouZh/CIPS-3D/piGAN_lib/datasets.py code served (permissive licence) · get_code("2172a94012703abe") |
| sample_generator | Not yet run | PeterouZh/CIPS-3D/piGAN_lib/extract_shapes.py code served (permissive licence) · get_code("3134951a7535b157") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses. The recently proposed NeRF-based GANs made great progress towards 3D-aware generators, but they are unable to generate high-quality images yet. This paper presents CIPS-3D, a style-based, 3D-aware generator that is composed of a shallow NeRF network and a deep implicit neural representation (INR) network. The generator synthesizes each pixel value independently without any spatial convolution or upsampling operation. In addition, we diagnose the problem of mirror symmetry that implies a suboptimal solution and solve it by introducing an auxiliary discriminator. Trained on raw, single-view images, CIPS-3D sets new records for 3D-aware image synthesis with an impressive FID of 6.97 for images at the $256\times256$ resolution on FFHQ. We also demonstrate several interesting directions for CIPS-3D such as transfer learning and 3D-aware face stylization. The synthesis results are best viewed as videos, so we recommend the readers to check our github project at https://github.com/PeterouZh/CIPS-3D
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2110.09788")
get_code_for_paper("2110.09788")
have("2110.09788")
Connect an agent — have() is free.