Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ tags:
|
|
| 16 |
|
| 17 |
HoloPASWIN (Physics-Aware Swin Transformer for Holographic Reconstruction) is a state-of-the-art model for eliminating twin-image artifacts and recovering complex object fields (amplitude and phase) from single-shot in-line holograms.
|
| 18 |
|
|
|
|
|
|
|
| 19 |
## Architecture
|
| 20 |
|
| 21 |
The model combines the exact physical model of free-space propagation with the powerful representation learning of a Swin Transformer.
|
|
@@ -42,6 +44,12 @@ HoloPASWIN v3 improves upon traditional CNN-based approaches and iterative solve
|
|
| 42 |
|
| 43 |
Evaluated on a test set of 496 holographic samples, HoloPASWIN v3 achieves excellent reconstruction fidelity in both amplitude and phase domains.
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
### Quantitative Metrics
|
| 46 |
|
| 47 |
| Metric | HoloPASWIN (Ours) | U-Net | ASM (Dirty) | GS (100 iter) |
|
|
|
|
| 16 |
|
| 17 |
HoloPASWIN (Physics-Aware Swin Transformer for Holographic Reconstruction) is a state-of-the-art model for eliminating twin-image artifacts and recovering complex object fields (amplitude and phase) from single-shot in-line holograms.
|
| 18 |
|
| 19 |
+
|
| 20 |
+
|
| 21 |
## Architecture
|
| 22 |
|
| 23 |
The model combines the exact physical model of free-space propagation with the powerful representation learning of a Swin Transformer.
|
|
|
|
| 44 |
|
| 45 |
Evaluated on a test set of 496 holographic samples, HoloPASWIN v3 achieves excellent reconstruction fidelity in both amplitude and phase domains.
|
| 46 |
|
| 47 |
+
### Qualitative Results
|
| 48 |
+
|
| 49 |
+
Below are sample reconstructions showing the Ground-Truth arrays juxtaposed against the Ground-Truth Amplitude & Phase, Zoomed Details, and Error Maps.
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
### Quantitative Metrics
|
| 54 |
|
| 55 |
| Metric | HoloPASWIN (Ours) | U-Net | ASM (Dirty) | GS (100 iter) |
|