DewarpNet-OpenVINO

DewarpNet for Intel NPUs, GPUs and CPUs: dewarp from litert-community/DewarpNet-LiteRT as ONNX (tf2onnx 1.17.0, opset 17), OpenVINO IR with fp32 weights, and a precompiled Intel NPU blob. On the NPU of a Core Ultra 9 386H the blob runs in 8.24 ms per run, numpy input to numpy output.

Scripts, raw records, and the same table for all 52 graphs of LiteRT-Models: https://github.com/john-rocky/windows-zoo

Files

file	bytes	sha256
dewarp.onnx	189,339,174	4dde2be5fa86a4b4b1dd870b0ba89dc5da6e2165b90992c13a96450935eb04c2
openvino/dewarp.xml	1,139,702	36060c9fd58b3fec9df7c95314892385f25240e9956a8005a05d2af914188e75
openvino/dewarp.bin	188,529,172	840b093d86a174c4694c0ff3a37a5270576bac67e4c2b4ff9737a279929f89bd
npu/dewarp.blob	19,378,305	345b2e8bb9239bf6df1e91a2ca8bad42ff83906e29087b755459cb61c9b669f3

The NPU blob was compiled with OpenVINO 2026.4.1, Intel NPU driver 32.0.100.4841 (OpenVINO reports NPU_DRIVER_VERSION 1004841, NPU_COMPILER_VERSION 524292). If import_model refuses a blob on another driver or OpenVINO version, compile the IR instead (the commented line in the snippet).

How it was measured

MSI Stealth 16 AI+ (Core Ultra 9 386H, RTX 5080 Laptop GPU at a 95 W power limit, Windows 11 build 26200.9711, on AC power), 2026-11-06 to 2026-11-07. On the laptop, each row is one process: load, one run, 5 warmup runs, then the median of 30 timed runs (2 warmup + 10 timed runs when the first run takes more than 3 s), numpy input to numpy output, every runtime at its default settings, one process at a time, each started after the CPU, the RTX and the Intel GPU had gone idle (the thresholds are in METHOD.md of the GitHub repo). Output check: each output against the CPU output in fp32 on the same input (ONNX Runtime's CPU EP); PASS = cosine ≥ 0.99, no NaN or Inf, and top-1 agreement ≥ 0.99 for class scores. The Snapdragon rows are Qualcomm AI Hub profile jobs of the same ONNX files (their own timer).

Speed and output check

processor	runtime	file	ms	load s	output check
Intel AI Boost NPU	OpenVINO 2026.4.1	npu/ blob (import_model)	8.24	0.01	PASS (cos ≥ 0.9999)
Intel AI Boost NPU	ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1	.onnx, compiled when the session loads	-	-	did not run
Intel Graphics (iGPU)	ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1	.onnx	9.07	1.74	FAIL: output_0_output: cos 0.9891 < 0.99
RTX 5080 Laptop (95 W limit)	ONNX Runtime 1.31.1, CUDA EP	fp16 copy of the .onnx (not in this repo)	6.74	1.51	PASS (cos ≥ 0.9999)
RTX 5080 Laptop (95 W limit)	ONNX Runtime 1.31.1, CUDA EP	.onnx	8.53	1.47	PASS (cos ≥ 0.9999)
Core Ultra 9 386H CPU	ONNX Runtime 1.31.1, CPU EP	.onnx	201.36	0.65	reference
Snapdragon X2 Elite NPU	Qualcomm AI Hub, precompiled QNN ONNX	.onnx compiled by AI Hub	5.04	0.34	not compared (AI Hub profile job, 2026-10-30)
Snapdragon X2 Elite NPU	Qualcomm AI Hub, ONNX Runtime QNN EP	.onnx, compiled when it loads	24.36 (19 layers on the CPU)	6.26	not compared (AI Hub profile job, 2026-10-30)
Galaxy S26 NPU	Qualcomm AI Hub, precompiled QNN ONNX	.onnx compiled by AI Hub	4.76	0.23	not compared (AI Hub profile job, 2026-10-30)

The ONNX file against the source .tflite (LiteRT interpreter on the CPU, the same input): PASS, cosine ≥ 0.9999 for every output.

Run it on the Intel NPU

Download this repo, then run the snippets from its folder:

pip install huggingface_hub
hf download mlboydaisuke/DewarpNet-OpenVINO --local-dir DewarpNet-OpenVINO
cd DewarpNet-OpenVINO

OpenVINO (pip install openvino==2026.4.1):

import numpy as np
import openvino as ov

core = ov.Core()
if "NPU" not in core.available_devices:
    raise SystemExit(f"no Intel NPU visible to OpenVINO: {core.available_devices}")
with open("npu/dewarp.blob", "rb") as f:
    compiled = core.import_model(f.read(), "NPU")  # precompiled: no compile at load
# or compile the IR on this machine: compiled = core.compile_model("openvino/dewarp.xml", "NPU")
# replace the zeros with your preprocessed input (float32, the shapes printed by compiled.inputs)
feeds = {i.get_any_name(): np.zeros(list(i.shape), np.float32) for i in compiled.inputs}
outputs = compiled(feeds)
print({o.get_any_name(): outputs[o].shape for o in compiled.outputs})

ONNX Runtime 1.31.1 with the OpenVINO EP 1.8.1 does not run dewarp.onnx on the NPU: the session fails to load (Compilation failed). The OpenVINO lines above run it.

Licence

MIT, the licence of litert-community/DewarpNet-LiteRT.