Omer Bar-Tal, Narek Tumanyan, Shai Bagon, Tali Dekel
We lifted 2 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 |
|---|---|---|
| omerbt/Splice | — | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| attn_cosine_sim | Ran | omerbt/Splice/models/extractor.py pointer only (licence: NONE) · get_code("e9f612ce15936ed2") |
| VitExtractor | Not yet run | omerbt/Splice/models/extractor.py pointer only (licence: NONE) · get_code("0784a33e97a3ce62") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Figure 1. Given two input images-a source structure image and a target appearance image-our method generates a new image in which the structure of the source image is preserved, while the visual appearance of the target image is transferred in a semantically aware manner. That is, objects in the structure image are "painted" with the visual appearance of semantically related objects in the appearance image. Our method leverages a self-supervised, pre-trained ViT model as an external semantic prior. This allows us to train our generator only on a single input image pair, without any additional information (e.g., segmentation/correspondences), and without adversarial training. Thus, our framework can work across a variety of objects and scenes, and can generate high quality results in high resolution (e.g., HD).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2201.00424")
get_code_for_paper("2201.00424")
have("2201.00424")
Connect an agent — have() is free.