Eric Lei, Hamed Hassani, Shirin Bidokhti, Yigit Berkay Uslu
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 |
|---|---|---|
| leieric/text-sketch | canonical | 1 of 1 |
| leieric/Text-Sketch | canonical | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| test_epoch | Ran | leieric/text-sketch/train_compressai.py pointer only (licence: NONE) · get_code("4d4553d8d2895e33") |
| recon_rcc | Not yet run | leieric/Text-Sketch/eval_PIC.py pointer only (licence: NONE) · get_code("89f31bd65cefbe30") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent advances in text-to-image generative models provide the ability to generate high-quality images from short text descriptions. These foundation models, when pre-trained on billion-scale datasets, are effective for various downstream tasks with little or no further training. A natural question to ask is how such models may be adapted for image compression. We investigate several techniques in which the pre-trained models can be directly used to implement compression schemes targeting novel low rate regimes. We show how text descriptions can be used in conjunction with side information to generate high-fidelity reconstructions that preserve both semantics and spatial structure of the original. We demonstrate that at very low bit-rates, our method can significantly improve upon learned compressors in terms of perceptual and semantic fidelity, despite no end-to-end training.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2307.01944")
get_code_for_paper("2307.01944")
have("2307.01944")
Connect an agent — have() is free.