README.md

---
license: apache-2.0
library_name: LiteRT
pipeline_tag: image-segmentation
tags: [litert, tflite, on-device, android, gpu, line-segment-detection, mlsd, wireframe, mobilenetv2]
base_model: navervision/mlsd
---

# M-LSD-tiny — LiteRT (on-device line segment detection, fully-GPU)

[M-LSD](https://github.com/navervision/mlsd) (NAVER, AAAI 2022) light-weight real-time **line segment
detection**, converted to **LiteRT** and running **fully on the `CompiledModel` GPU** (ML Drift) on Android.
Detects straight line segments — building edges, document borders, wireframes, room layout. The **tiny**
variant (MobileNetV2 backbone, 0.62M params) is **1.4 MB** in fp16.

![M-LSD — input | detected line segments (on-device LiteRT GPU)](samples/sample.png)

## On-device (Pixel 8a, Tensor G3 — verified)

| | |
|---|---|
| nodes on GPU | **99 / 99** LITERT_CL (full residency) |
| inference | **~2 ms** (512×512) |
| size | **1.4 MB** (fp16) |
| accuracy | device-vs-PyTorch corr **0.997** (127 vs 128 lines decoded) |

```
image[1,4,512,512] (RGB + ones channel, scaled to [-1,1]) →[GPU: MobileNetV2 U-Net]→ tpMap[1,9,256,256]
```

The output is a "TP map": channel 0 = line-center heatmap, channels 1–4 = start/end displacement. The decode
(sigmoid + 3×3 NMS over centers, displacement → endpoints, ×2) runs on the host.

## How it converts (litert-torch)

Pure CNN encoder-decoder. A single re-authoring: the decoder's `F.interpolate(bilinear, align_corners=True)`
→ **`align_corners=False`** (the Mali delegate bans `align_corners=True` + half-pixel). MobileNetV2 has no
max-pool (strided convs → no `PADV2`), and the upsample is `RESIZE_BILINEAR`, not a transposed conv → fully
GPU-clean. Result: banned ops NONE, all tensors ≤4D, tflite-vs-torch corr **1.0**, device-vs-torch corr **0.997**.

## Preprocessing & decode

Resize to 512×512, append a 4th channel of ones, scale `(x/127.5) - 1`, NCHW. Decode: sigmoid the center map,
3×3 max NMS, threshold (0.10), displacement → endpoints, filter by length, ×2 to 512-space.

## Minimal usage

**Android (Kotlin, CompiledModel GPU)**

```kotlin
val model = CompiledModel.create(context.assets, "mlsd_fp16.tflite",
    CompiledModel.Options(Accelerator.GPU), null)
val inputs = model.createInputBuffers(); val outputs = model.createOutputBuffers()
inputs[0].writeFloat(x)             // [1,4,512,512] NCHW: RGB + ones channel, x/127.5 - 1
model.run(inputs, outputs)
val tpMap = outputs[0].readFloat()  // [1,9,256,256]: ch0 center, ch1-4 displacement
// sigmoid + 3x3 NMS + displacement -> segments: port of the Python decode below.
```

**Python (desktop verification)**

```python
import numpy as np
from PIL import Image
from scipy.ndimage import maximum_filter
from ai_edge_litert.interpreter import Interpreter

im = Image.open("photo.jpg").convert("RGB").resize((512, 512))
a = np.asarray(im, np.float32)
a = np.concatenate([a, np.ones((512, 512, 1), np.float32)], -1)   # 4th channel of ones
x = ((a.transpose(2, 0, 1)[None] / 127.5) - 1.0).copy()           # [1,4,512,512]

it = Interpreter(model_path="mlsd_fp16.tflite"); it.allocate_tensors()
it.set_tensor(it.get_input_details()[0]["index"], x); it.invoke()
tp = it.get_tensor(it.get_output_details()[0]["index"])[0]        # [9,256,256]

center = 1 / (1 + np.exp(-tp[0])); disp = tp[1:5]
peak = (center == maximum_filter(center, 3)) & (center > 0.10)    # 3x3 NMS + threshold
ys, xs = np.where(peak)
order = center[ys, xs].argsort()[::-1][:200]                      # top-200 centers
lines = []
for y, x0 in zip(ys[order], xs[order]):
    dxs, dys, dxe, dye = disp[:, y, x0]
    if np.hypot(dxs - dxe, dys - dye) > 20:                       # min segment length (px)
        lines.append([(x0 + dxs) * 2, (y + dys) * 2, (x0 + dxe) * 2, (y + dye) * 2])
print(f"{len(lines)} line segments (x0,y0,x1,y1 in 512-space)")
```

## License

[Apache-2.0](https://github.com/navervision/mlsd/blob/main/LICENSE). Upstream:
[navervision/mlsd](https://github.com/navervision/mlsd); PyTorch port [lhwcv/mlsd_pytorch](https://github.com/lhwcv/mlsd_pytorch).