We lifted 9 functions out of this paper's own repositories and ran 7 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 |
|---|---|---|
| open-mmlab/StyleShot | canonical | 6 of 8 |
| Vill-Lab/forkOfStyleShot | reimplementation | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| FeedForward | Ran | open-mmlab/StyleShot/ip_adapter/resampler.py code served (permissive licence) · get_code("5105747c2711b1cb") |
| HWC3 | Ran | open-mmlab/StyleShot/annotator/util.py code served (permissive licence) · get_code("f9ec7d70add02b6f") |
| collate_fn | Ran | Vill-Lab/forkOfStyleShot/tutorial_train_styleshot_stage_1.py code served (permissive licence) · get_code("fcae89892257d1c0") |
| collate_fn | Ran | open-mmlab/StyleShot/tutorial_train_styleshot_stage_2.py code served (permissive licence) · get_code("899f518fa323466c") |
| masked_mean | Ran | open-mmlab/StyleShot/ip_adapter/resampler.py code served (permissive licence) · get_code("230588e8f1237737") |
| nms | Ran | open-mmlab/StyleShot/annotator/util.py code served (permissive licence) · get_code("fa18e29c0ab322c6") |
| reshape_tensor | Ran | open-mmlab/StyleShot/ip_adapter/resampler.py code served (permissive licence) · get_code("4cb2e2a2ca0bec9f") |
| StyleProcessor | Not yet run | open-mmlab/StyleShot/ip_adapter/ip_adapter.py code served (permissive licence) · get_code("b6a399852dc888c3") |
| resize_image | Not yet run | open-mmlab/StyleShot/annotator/util.py code served (permissive licence) · get_code("50fd68f6989503c6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a style-aware encoder and a well-organized style dataset called StyleGallery. With dedicated design for style learning, this style-aware encoder is trained to extract expressive style representation with decoupling training strategy, and StyleGallery enables the generalization ability. We further employ a content-fusion encoder to enhance image-driven style transfer. We highlight that, our approach, named StyleShot, is simple yet effective in mimicking various desired styles, i.e., 3D, flat, abstract or even fine-grained styles, without test-time tuning. Rigorous experiments validate that, StyleShot achieves superior performance across a wide range of styles compared to existing state-of-the-art methods. The project page is available at: https://styleshot.github.io/.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.01414")
get_code_for_paper("2407.01414")
have("2407.01414")
Connect an agent — have() is free.