Update README.md
Browse files
README.md
CHANGED
@@ -111,15 +111,15 @@ We find that compared to the baseline model SD 2.1, we largely improve the spati
|
|
111 |
|
112 |
The following table compares our SPRIGHT-T2I model with SD 2.1 across multiple spatial reasoning and image quality:
|
113 |
|
114 |
-
|Method |OA(%) β|VISOR-4(%) β|T2I-CompBench β|FID β|
|
115 |
|------------------|-------|------------|---------------|-----|------|
|
116 |
|SD v2.1 |47.83 |4.70 |0.1507 |21.646|1.060 |
|
117 |
|SPRIGHT-T2I (ours)|60.68 |16.15 |0.2133 |16.149|0.512 |
|
118 |
|
119 |
Our key findings are:
|
120 |
-
-
|
121 |
-
-
|
122 |
-
- Improve on all aspects of the VISOR score while improving the ZS-FID and CMMD score on COCO-30K images by 23.74% and 51.69%, respectively
|
123 |
- Enhance the ability to generate 1 and 2 objects, along with generating the correct number of objects, as indicated by evaluation on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
|
124 |
|
125 |
### Model Resources
|
|
|
111 |
|
112 |
The following table compares our SPRIGHT-T2I model with SD 2.1 across multiple spatial reasoning and image quality:
|
113 |
|
114 |
+
|Method |OA(%) β|VISOR-4(%) β|T2I-CompBench β|FID β|CMMD β|
|
115 |
|------------------|-------|------------|---------------|-----|------|
|
116 |
|SD v2.1 |47.83 |4.70 |0.1507 |21.646|1.060 |
|
117 |
|SPRIGHT-T2I (ours)|60.68 |16.15 |0.2133 |16.149|0.512 |
|
118 |
|
119 |
Our key findings are:
|
120 |
+
- We increase the VISOR Object Accuracy (OA) score by 26.86%, indicating that we are much better at generating objects mentioned in the input prompt.
|
121 |
+
- VISOR-4 score of 16.15% denotes that for a given input prompt, we consistently generate a spatially accurate image.
|
122 |
+
- Improve on all aspects of the VISOR score while improving the ZS-FID and CMMD score on COCO-30K images by 23.74% and 51.69%, respectively.
|
123 |
- Enhance the ability to generate 1 and 2 objects, along with generating the correct number of objects, as indicated by evaluation on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
|
124 |
|
125 |
### Model Resources
|