Spaces:
Running
on
Zero
Running
on
Zero
| import gradio as gr | |
| import spaces | |
| from src.utils import * | |
| from src.backend import * | |
| theme = gr.themes.Soft(primary_hue="cyan", secondary_hue="zinc", font=[gr.themes.GoogleFont("Source Sans 3", weights=(400, 600)),'arial']) | |
| with gr.Blocks(theme=theme) as demo: | |
| with gr.Column(elem_classes="header"): | |
| gr.HTML('<img src="https://huggingface.co/spaces/mikonvergence/COP-GEN-Beta/resolve/main/logos/COP-GEN-logo.png" style="max-width: 90%; width:300px;">') | |
| gr.Markdown("# 🔵 COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails") | |
| gr.Markdown("### Miguel Espinosa, Valerio Marsocci, Yuru Jia, Elliot J. Crowley, Mikolaj Czerkawski") | |
| gr.HTML('<a href="https://github.com/miquel-espinosa/COP-GEN-Beta" class="text-decoration-none site-link"><img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/miquel-espinosa/COP-GEN-Beta"></a>') | |
| #gr.Markdown('[[Website](https://miquel-espinosa.github.io/cop-gen-beta/)] [GitHub](https://github.com/miquel-espinosa/COP-GEN-Beta)] [[Model](https://huggingface.co/mespinosami/COP-GEN-Beta) [[Dataset](https://huggingface.co/Major-TOM)]') | |
| gr.Markdown('> ## ⚠️ NOTE: This is a prototype Beta model of COP-GEN. It is based on image thumbnails of [Major TOM](https://huggingface.co/Major-TOM) and does not yet support raw source data. The hillshade visualisation is used for elevation. The full model COP-GEN is coming soon.') | |
| with gr.Column(elem_classes="Main app"): | |
| with gr.Accordion("Instructions", open=False) as abstract: | |
| gr.Markdown("1. **Generate**: Click the `🏭 Generate` button to synthesize the output **without any conditions**. The outputs will be shown below - and that's it, you've generated your first sample! 🧑🎨️"+ | |
| "<br/>2. **Optionally, define input**: If you want to condition your generation, you can upload your thumbnails manually or you can `🔄 Load` a random sample from Major TOM by clicking the button."+ | |
| "<br/>3. **Select conditions**: Each input image can be used as a **conditioning** when it's loaded into the inputs panel. The modalities you wish to generate should have no content in the input panel (you can empty each element by clicking `x` in the top right corner of the image)."+ | |
| "<br/>4. **Additional Options**: You can control the number of generation steps (higher number might produce better quality, but will take more time), or set a fixed seed (for reproducible results)."+ | |
| "<br/>5. You can also reuse any of the generated samples as input to the model by clicking `♻️ Reuse`") | |
| with gr.Column(): | |
| generate_button = gr.Button("🏭 Generate", variant="primary") | |
| gr.Markdown("## Outputs") | |
| with gr.Row(): | |
| s2l1c_output = gr.Image(label="S2 L1C (Optical - Top of Atmosphere)", interactive=False) | |
| s2l2a_output = gr.Image(label="S2 L2A (Optical - Bottom of Atmosphere)", interactive=False) | |
| s1rtc_output = gr.Image(label="S1 RTC (SAR)", interactive=False) | |
| dem_output = gr.Image(label="DEM (Elevation)", interactive=False) | |
| with gr.Row(): | |
| s2l1c_reuse_button = gr.Button("♻️ Reuse S2 L1C as input ⤵️", variant="primary") | |
| s2l2a_reuse_button = gr.Button("♻️ Reuse S2 L2A as input ⤵️", variant="primary") | |
| s1rtc_reuse_button = gr.Button("♻️ Reuse S1 RTC as input ⤵️", variant="primary") | |
| dem_reuse_button = gr.Button("♻️ Reuse DEM as input ⤵️", variant="primary") | |
| gr.Markdown("---") | |
| with gr.Row(): | |
| gr.Markdown("## (Optional) Input Conditions") | |
| load_button = gr.Button("🔄 Load a random sample from Major TOM 🗺", variant="secondary") | |
| with gr.Row(): | |
| s2l1c_input = gr.Image(label="S2 L1C (Optical - Top of Atmosphere)", interactive=True) | |
| s2l2a_input = gr.Image(label="S2 L2A (Optical - Bottom of Atmosphere)", interactive=True) | |
| s1rtc_input = gr.Image(label="S1 RTC (SAR)", interactive=True) | |
| dem_input = gr.Image(label="DEM (Elevation)", interactive=True) | |
| gr.Markdown('### Ready? Go back up and press `🏭 Generate` again!') | |
| with gr.Accordion("Advanced Options", open=False) as advanced_options: | |
| num_inference_steps_slider = gr.Slider(minimum=10, maximum=1000, step=10, value=10, label="Inference Steps") | |
| with gr.Row(): | |
| seed_number = gr.Number(value=6378, label="Seed") | |
| seed_checkbox = gr.Checkbox(value=True, label="Random") | |
| with gr.Accordion("Abstract", open=False) as abstract: | |
| gr.HTML('<a href="https://arxiv.org/abs/2504.08548/" class="text-decoration-none site-link"><img alt="Arxiv Link" src="https://img.shields.io/badge/Open_Access-arxiv:2504.08548-b31b1b"></a>') | |
| gr.Markdown("In remote sensing, multi-modal data from various sensors capturing the same scene offers rich opportunities, but learning a unified representation across these modalities remains a significant challenge. Traditional methods have often been limited to single or dual-modality approaches. In this paper, we introduce COP-GEN-Beta, a generative diffusion model trained on optical, radar, and elevation data from the Major TOM dataset. What sets COP-GEN-Beta apart is its ability to map any subset of modalities to any other, enabling zero-shot modality translation after training. This is achieved through a sequence-based diffusion transformer, where each modality is controlled by its own timestep embedding. We extensively evaluate COP-GEN-Beta on thumbnail images from the Major TOM dataset, demonstrating its effectiveness in generating high-quality samples. Qualitative and quantitative evaluations validate the model's performance, highlighting its potential as a powerful pre-trained model for future remote sensing tasks.") | |
| load_button.click( | |
| fn=sample_shuffle, | |
| outputs=[s2l1c_input,s2l2a_input,s1rtc_input,dem_input] | |
| ) | |
| generate_button.click( | |
| fn=generate_output, | |
| inputs=[s2l1c_input, | |
| s2l2a_input, | |
| s1rtc_input, | |
| dem_input, | |
| num_inference_steps_slider, seed_number, seed_checkbox], | |
| outputs=[s2l1c_output, s2l2a_output, s1rtc_output, dem_output], | |
| ) | |
| def pass_value(value): | |
| return value | |
| s2l1c_reuse_button.click(fn=pass_value, inputs=[s2l1c_output],outputs=[s2l1c_input]) | |
| s2l2a_reuse_button.click(fn=pass_value, inputs=[s2l2a_output],outputs=[s2l2a_input]) | |
| s1rtc_reuse_button.click(fn=pass_value, inputs=[s1rtc_output],outputs=[s1rtc_input]) | |
| dem_reuse_button.click(fn=pass_value, inputs=[dem_output],outputs=[dem_input]) | |
| demo.queue().launch(share=True) |