OCR-Format
#5
by BigTiger78 - opened
README.md
CHANGED
|
@@ -47,10 +47,6 @@ This is the PP-Doclayoutv3 model weights for the PaddlePaddle framework. Get saf
|
|
| 47 |
|
| 48 |
**PP-DocLayoutV3 is specifically engineered to handle non-planar document images. It can directly predict multi-point bounding boxes for layout elements—as opposed to standard two-point boxes—and determine logical reading orders for skewed and curved surfaces within a single forward pass, significantly reducing cascading errors.** This model is an essential component of PaddleOCR-VL-1.5, providing crucial layout analysis for the high-precision parsing of various real-world documents in PaddleOCR-VL.
|
| 49 |
|
| 50 |
-
This work has been accepted to ECCV 2026! 🎉
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
|
| 55 |
### **Model Architecture**
|
| 56 |
|
|
|
|
| 47 |
|
| 48 |
**PP-DocLayoutV3 is specifically engineered to handle non-planar document images. It can directly predict multi-point bounding boxes for layout elements—as opposed to standard two-point boxes—and determine logical reading orders for skewed and curved surfaces within a single forward pass, significantly reducing cascading errors.** This model is an essential component of PaddleOCR-VL-1.5, providing crucial layout analysis for the high-precision parsing of various real-world documents in PaddleOCR-VL.
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
### **Model Architecture**
|
| 52 |
|