FRENKIE-CHIANG commited on
Commit
c9835d3
·
verified ·
1 Parent(s): 8bc367f

Upload app.py with huggingface_hub

Browse files
Files changed (1) hide show
  1. app.py +16 -16
app.py CHANGED
@@ -342,28 +342,28 @@ with gr.Blocks(
342
  )
343
 
344
  gr.Markdown(
345
- r"""
346
- ### 📊 Overall Score Definition
347
 
348
- To facilitate clearer and more consistent comparison across models, we introduce an **Overall** score for each leaderboard track.
349
 
350
- **1. OmniLLM / MLLM**
351
- The **Overall** score is computed as the arithmetic mean of all reported task-specific scores.
352
 
353
- **2. Image Generation**
354
- The evaluation involves metrics defined on different numerical scales. **WIScore** is used for image generation, while **VIEScore** (averaged over three dimensions) is used for image editing.
355
- The **Overall** score is defined as:
356
 
357
- \[
358
- \text{Overall}=\frac{(\text{WIScore}\times 10)+\left(\frac{\sum \text{VIEScore}}{3}\right)}{2}
359
- \]
360
 
361
- This normalization-based formulation ensures a balanced contribution from both image generation and image editing performance.
362
 
363
- **3. Video Generation**
364
- The **Overall** score is calculated as the arithmetic mean of all evaluated dimensions, including imaging quality, aesthetics, motion, and temporal consistency.
365
- """
366
- )
367
 
368
  demo.launch()
369
 
 
342
  )
343
 
344
  gr.Markdown(
345
+ r"""
346
+ ### 📊 Overall Score Definition
347
 
348
+ To facilitate clearer and more consistent comparison across models, we introduce an **Overall** score for each leaderboard track.
349
 
350
+ **1. OmniLLM / MLLM**
351
+ The **Overall** score is computed as the arithmetic mean of all reported task-specific scores.
352
 
353
+ **2. Image Generation**
354
+ The evaluation involves metrics defined on different numerical scales. **WIScore** is used for image generation, while **VIEScore** (averaged over three dimensions) is used for image editing.
355
+ The **Overall** score is defined as:
356
 
357
+ $$
358
+ \text{Overall}=\frac{(\text{WIScore}\times 10)+\left(\frac{\sum \text{VIEScore}}{3}\right)}{2}
359
+ $$
360
 
361
+ This normalization-based formulation ensures a balanced contribution from both image generation and image editing performance.
362
 
363
+ **3. Video Generation**
364
+ The **Overall** score is calculated as the arithmetic mean of all evaluated dimensions, including imaging quality, aesthetics, motion, and temporal consistency.
365
+ """
366
+ )
367
 
368
  demo.launch()
369