English | 中文

Sdcb.SimdGcdrNet is a pure C# implementation of GCDRNet (Appearance Enhancement for Camera-captured Document Images in the Wild, IEEE TAI 2023) — document-image shadow removal and appearance enhancement without onnxruntime or any other third-party inference engine. Inference runs on Sdcb.SimdOnnx, a pure C# engine shared with Sdcb.SimdPaddleOCR (it grew out of this repository's own engine).

The model is a two-stage pipeline:

1. GC-Net predicts a per-pixel multiplicative shading/illumination map I_sm.
2. Division correction: I_GC = clamp(I_s / I_sm, 0, 1).
3. DR-Net consumes the 6-channel input [I_s; I_GC] and produces the enhanced image.

• Zero inference-engine dependency — self-contained ONNX proto reader, graph compiler (shape specialization, constant folding, operator fusion, buffer-arena planning).
• CPU backend with ISA tiered dispatch: AVX-512 → AVX2 (+FMA, multithreaded) → Vector<float> → Scalar on x64; NEON (AArch64 AdvSimd) → Scalar on arm64; PackedSimd (WASM SIMD128) → Vector<float> → Scalar on browser-wasm.
• Vulkan compute backend (Windows/Linux/Android libvulkan): push-descriptors, ReBAR-aware staging, single-recorded-command-buffer graph execution: pixels → GC → division → DR → pixels as one model and one submit per image, with arbitrary source/destination strides.
• Metal compute backend (macOS, Apple Silicon): pure C# ObjC P/Invoke (no Xamarin/Metal.NET), fp16 storage + fp32 math, simdgroup-MMA implicit-GEMM convolutions — see docs/apple-m4-metal.md (~7.5× CPU on M4).
• Any interleaved 8-bit layout (Bgr24 / Rgb24 / Bgra32 / Rgba32), arbitrary strides, in place; thread-safe GcdrEnhancer; Native AOT compatible.

Ryzen AI 9 H 365 (AVX-512) + Radeon 880M (RDNA 3.5 iGPU): see docs/amd-h365-880m.md (Vulkan ~100 ms/img, CPU AVX-512 ~285 ms/img on the same corpus).

Ryzen 9 5950X (AVX2, 16C/32T) + Intel Arc B580 (Xe2, XMX via 8x16x16 coopmat): see docs/amd-5950x-b580.md (Vulkan ~36 ms/img, CPU AVX2 ~414 ms/img on the same corpus).

Rockchip RK3399 (2× A72 + 4× A53, NEON, passively cooled): see docs/rockchip-rk3399.md (CPU NEON ~9.0 s/img on the same corpus, 2.6× the generic Vector<float> path at a locked 1 GHz).

Snapdragon 8 Gen 3 (realme GT5 Pro, Android 16; Adreno 750 without coopmat, 64/128-lane waves): see docs/snapdragon-8gen3.md (Vulkan ~486 ms/img with register-tiled conv/GEMM kernels, 2.6× the shared-memory path; CPU NEON ~1.03 s/img on the same corpus).

Browser (browser-wasm, WASM SIMD128, Web Workers threads, LLVM AOT): see docs/wasm.md (Edge on a 5950X: CPU PackedSimd ~696 ms/img on the same corpus, 1.55× the generic Vector<float> path in the same browser).

Requires .NET 10: both packages target net10.0 only.

using Sdcb.SimdGcdrNet;
using Sdcb.SimdGcdrNet.Models;

// Auto: Metal on macOS Apple Silicon, else Vulkan, else CPU. Also: Cpu (default) / Vulkan / Metal.
using GcdrEnhancer enh = GcdrEnhancer.FromBytes(GcdrModels.GcNet, GcdrModels.DrNet, GcdrBackend.Auto);
// without the models package: GcdrEnhancer.FromFiles("gcdrnet_gcnet_sim.onnx", "gcdrnet_drnet_sim.onnx", ...)
// (models in tests/testdata/models), or FromBytes(span, span) / FromStreams(stream, stream)

byte[] dst = enh.Enhance(bgr, width: 1600, height: 1152);   // tightly packed BGR24, HWC
// strided, any interleaved 8-bit layout, output in the same layout (alpha copied through):
enh.Enhance(srcSpan, w, h, srcStride, dstSpan, dstStride, GcdrPixelFormat.Rgba32);

Pixel formats: Bgr24 (OpenCV Mat, GDI+ 24bpp), Rgb24, Bgra32 (SkiaSharp, GDI+ 32bpp), Rgba32 (ImageSharp, browser canvas). dst may be the same buffer as src (same stride) for in-place enhancement.

Input is padded to a multiple of 32 with top/left replicate padding and cropped back — matching the reference Python implementation.

The three UI examples open examples/example.jpg (a phone photo of a hand-drawn poster with a hard hand shadow):

• examples/SimdCodecs.AspNetCore — ASP.NET Core + SimdCodecs (ImageCodecs.Decode with ApplyOrientation into one Rgba32 buffer, enhanced in place; a bad upload returns the codec's own error message): upload / drag-and-drop, before-after slider, auto / cpu backend switch, timings; POST /api/enhance returns the enhanced image (API docs at /scalar).
• examples/SkiaSharp.Avalonia — cross-platform desktop (Windows / Linux / macOS, Bgra32 SKBitmap): side-by-side preview, auto / cpu / vulkan (metal on macOS) switch, save as JPEG / PNG.
• examples/OpenCvSharp5.Wpf — WPF + OpenCvSharp5 (Bgr24 Mat, any Step()): same UI, plus drag-and-drop.
• examples/PaddleOCR.Console — enhance with SimdGcdrNet, then OCR the original and the enhanced image with SimdPaddleOCR; both take the same decoded RGBA buffer. Its default examples/ocr-example.jpg (from RealDAE) has heavy show-through from the back of the page: OCR on the original returns 56 lines (mostly garbage from the back side), on the enhanced image the 14 real lines.

dotnet run --project examples/SimdCodecs.AspNetCore        # http://localhost:5190
dotnet run --project examples/SkiaSharp.Avalonia -- [image]
dotnet run --project examples/OpenCvSharp5.Wpf -- [image]
dotnet run --project examples/PaddleOCR.Console -- [image] [output.jpg]

The ONNX engine (protobuf reader, graph compiler, CPU SIMD kernels, Vulkan / Metal backends) is Sdcb.SimdOnnx; this library holds the GCDRNet-specific parts:

• src/Sdcb.SimdGcdrNet/GcdrEnhancer.cs — public API: backend selection, session pools, and the composed model (GC-Net → clamp(x / max(shading, 1e-6), 0, 1) → DR-Net, built with OnnxModelBuilder) that runs on SimdOnnx's CpuSession and VkImageSession / MtlImageSession. The library uses only SimdOnnx's public API; the fusions it needs (UpHead, ChannelShift, SafeDiv) are engine built-ins.
• bench/Sdcb.SimdGcdrNet.Benchmark — --check, --bench (CPU), --benchvk (Vulkan e2e), --benchmtl / --checkgpu / --mtlprof / --mtrace (Metal e2e, diff check, per-shader profile, CPU-vs-Metal per-node trace), --vkprof (per-shader/per-dispatch GPU timing), --vkcheck / --vknodes (Vulkan vs CPU, whole graph / per node)
• bench/Sdcb.SimdGcdrNet.AndroidBench — the same modes inside an Android APK (run.ps1: build → adb install → push testdata → run → pull logs)
• bench/Sdcb.SimdGcdrNet.WasmBench — --corpus / --bench / --check / --tiers in a browser (run.ps1: publish with LLVM AOT → server.mjs with COOP/COEP → headless Edge/Chrome); needs the wasm-tools-net10 workload and Node.js
• src/Sdcb.SimdGcdrNet.Models — GcdrModels over the embedded ONNX files (taken from tests/testdata/models)
• src/Sdcb.SimdGcdrNet/linqpad-samples — LINQPad samples packed into Sdcb.SimdGcdrNet (tag linqpad-samples)
• tests/Sdcb.SimdGcdrNet.Tests — xUnit tests; tests/GoldenDerive.cs recomputes the derived golden data; tests/Sdcb.SimdGcdrNet.TestReport merges CI results into a markdown report
• tools/fetch-fixture.ps1 — downloads the RealDAE corpus; tools/GenGolden regenerates the golden data
• build/ — LINQPad scripts to pack (01-build-packages) and publish (02-publish-proget-nuget) the packages; versions live in 00-common.linq and Directory.Build.props

./tools/fetch-fixture.ps1                          # RealDAE corpus (~36 MB) -> tests/testdata/realdae
dotnet test tests/Sdcb.SimdGcdrNet.Tests -c Release

Golden data comes from onnxruntime runs of the simplified models (CPU ≤ 1e-4 / Vulkan ≤ 5e-4): only the source {tag}_src.png and the two oracle outputs (_shadow.f32, _output.f32) are committed; the GC-Net input, the DR-Net input and the final u8 image are recomputed bit-exactly by tests/GoldenDerive.cs. Regenerate with dotnet run --project tools/GenGolden -- --models tests/testdata/models (pure C#: OnnxRuntime oracle + SkiaSharp decode).

The 50-image RealDAE corpus (NN_<color|shadow|bleed>.webp + paired NN_gt.webp ground truths) lives in sdcb/DocGainFixture; without it CorpusTests are skipped. The benchmark's --corpus [cpu|vulkan|metal] mode reports per-image ms, MP/s, memory and PSNR/MAE vs the _gt pairs.

Kernel dispatch follows the runtime's IsSupported flags, so ISA tiers are exercised via the standard runtime knobs: DOTNET_EnableAVX512=0 / DOTNET_EnableAVX512F=0 (AVX2), DOTNET_EnableAVX2=0 (128-bit Vector<float>), DOTNET_EnableAVX=0 (SSE, no FMA) and DOTNET_EnableHWIntrinsic=0 (scalar).

CI (.github/workflows/test.yml) runs two waves in parallel, then merges them into one report (the run's summary page):

• smoke: dotnet test plus a corpus smoke (Benchmark --ci smoke: sane, deterministic output that is closer to the ground truth than the input; GPU output close to CPU) on win-x64, win-arm64, linux-x64, linux-arm64, osx-x64 and osx-arm64 (CPU and Metal), plus the x64 ISA tiers above and arm64 scalar;
• bench: Benchmark --ci bench on 20 corpus images, several replicas per case: win-x64 (default, no AVX-512, no AVX2), linux-x64, linux-arm64 (NEON) and osx-arm64 (CPU, Metal).

• Vulkan path requires a compute-capable device; GcdrBackend.Auto falls back to CPU.

• Metal path requires macOS on Apple Silicon with Apple7+ (simdgroup-MMA, i.e. M1+; an x64 process under Rosetta also qualifies); Auto checks SupportsApple7 before choosing it, GcdrBackend.Metal selects it unconditionally. Set GCDRNET_MTL_VERBOSE=1 to print the chosen device.

• Thread-safety: GcdrEnhancer is thread-safe (CPU: per-size session pools; Vulkan: size-agnostic worker pool).

• 2.0 moved the engine out: InferenceSession, CompiledModel, OnnxModel, VkInferenceSession and MtlInferenceSession are no longer in Sdcb.SimdGcdrNet.*; use the same types from Sdcb.SimdOnnx.* (a dependency of this package). GcdrEnhancer's API is unchanged.

• Not covered: batched inference (N>1), fp16/int8.

• Native AOT works (IsAotCompatible, no trim/AOT warnings; CPU and Vulkan output verified identical to JIT). On x64 the executable project must set the instruction set, otherwise ILC compiles for the SSE baseline, folds Avx2.IsSupported / Avx512F.IsSupported to false and the CPU backend silently runs the 128-bit Vector<float> tier (~1.3× slower):

  <IlcInstructionSet>x86-64-v3</IlcInstructionSet>   <!-- AVX2+FMA; x86-64-v4 for AVX-512 -->

  The binary then refuses to start on CPUs without those extensions. arm64 needs nothing (NEON is in the baseline); GPU backends are unaffected.

The inference engine (Sdcb.SimdGcdrNet, everything outside src/Sdcb.SimdGcdrNet.Models) is Apache-2.0. Sdcb.SimdGcdrNet.Models is MIT, following the upstream GCDRNet weights it embeds (Copyright (c) 2024 Jiaxin Zhang); see THIRD-PARTY-NOTICES.txt, also shipped in both packages. The test corpus (sdcb/DocGainFixture) and examples/ocr-example.jpg are from the RealDAE dataset of the same paper.

Sdcb.SimdGcdrNet 是 GCDRNet（相机拍摄文档去阴影/外观增强， IEEE TAI 2023）的纯 C# 推理库——不依赖 onnxruntime 等第三方推理引擎，与 Sdcb.SimdPaddleOCR 共用纯 C# 推理引擎 Sdcb.SimdOnnx（2.0 起引擎类型移到 Sdcb.SimdOnnx.*）。

模型为两级串联：GC-Net 估计逐像素光照/阴影图 I_sm → I_GC = clamp(I_s/I_sm) 除法校正 → DR-Net 消费 6 通道 [I_s; I_GC] 输出增强图。

• 零推理引擎依赖：自带 ONNX proto 读取 + 图编译（shape 特化、常量折叠、算子融合、arena 规划）
• CPU 后端：x64 上 AVX-512 → AVX2+FMA 多线程 → Vector<float> → Scalar 四档 ISA 自动分发；arm64 上 NEON（AdvSimd）→ Scalar；browser-wasm 上 PackedSimd（WASM SIMD128）→ Vector<float> → Scalar
• Vulkan 后端：push-descriptor、ReBAR 感知 staging、单命令缓冲图执行、 像素 → GC → 除法校正 → DR → 像素合成一个模型、每张图一次提交，支持任意 src/dst stride
• Metal 后端（macOS，Apple Silicon）：纯 C# ObjC P/Invoke（不依赖 Xamarin/Metal.NET），fp16 存储 + fp32 计算， simdgroup-MMA 隐式 GEMM 卷积，见 docs/apple-m4-metal.md（M4 上约为 CPU 的 7.5 倍）
• 任意 8 位交错像素格式（Bgr24 / Rgb24 / Bgra32 / Rgba32），任意 stride，支持原地增强； GcdrEnhancer 线程安全；兼容 Native AOT

锐龙 AI 9 H 365（AVX-512）+ Radeon 880M（RDNA 3.5 核显）见 docs/amd-h365-880m.md （同一语料 Vulkan ~100 ms/张，CPU AVX-512 ~285 ms/张）。

锐龙 9 5950X（AVX2，16C/32T）+ Intel Arc B580（Xe2，8x16x16 coopmat 走 XMX）见 docs/amd-5950x-b580.md （同一语料 Vulkan ~36 ms/张，CPU AVX2 ~414 ms/张）。

瑞芯微 RK3399（2× A72 + 4× A53，NEON，被动散热）见 docs/rockchip-rk3399.md （同一语料 CPU NEON ~9.0 s/张；锁 1 GHz 时是通用 Vector<float> 路径的 2.6 倍）。

骁龙 8 Gen 3（真我 GT5 Pro，Android 16；Adreno 750 无 coopmat，64/128 lane wave）见 docs/snapdragon-8gen3.md （同一语料 Vulkan ~486 ms/张，寄存器分块卷积/GEMM 内核比共享内存路径快 2.6 倍；CPU NEON ~1.03 s/张）。

浏览器（browser-wasm，WASM SIMD128，Web Workers 多线程，LLVM AOT）见 docs/wasm.md （5950X 上的 Edge：同一语料 CPU PackedSimd ~696 ms/张，是同浏览器通用 Vector<float> 路径的 1.55 倍）。

需要 .NET 10：两个包都只面向 net10.0。

using Sdcb.SimdGcdrNet;
using Sdcb.SimdGcdrNet.Models;

// Auto：macOS Apple Silicon 优先 Metal，否则 Vulkan，最后 CPU；也可显式 Cpu（默认）/ Vulkan / Metal
using GcdrEnhancer enh = GcdrEnhancer.FromBytes(GcdrModels.GcNet, GcdrModels.DrNet, GcdrBackend.Auto);
// 不用模型包：GcdrEnhancer.FromFiles("gcdrnet_gcnet_sim.onnx", "gcdrnet_drnet_sim.onnx", ...)
// （模型见 tests/testdata/models），或 FromBytes(span, span) / FromStreams(stream, stream)

byte[] dst = enh.Enhance(bgrBytes, width: 1600, height: 1152);   // 紧密排列的 BGR24，HWC
// 带 stride、任意 8 位交错格式，输出与输入同格式（alpha 原样拷回）：
enh.Enhance(src, w, h, srcStride, dst, dstStride, GcdrPixelFormat.Rgba32);

像素格式：Bgr24（OpenCV Mat、GDI+ 24bpp）、Rgb24、Bgra32（SkiaSharp、GDI+ 32bpp）、 Rgba32（ImageSharp、浏览器 canvas）。dst 可以和 src 是同一块内存（stride 相同），即原地增强。

输入补齐到 32 倍数（上/左 replicate padding），输出自动裁回，与参考 Python 实现一致。

三个界面示例默认打开 examples/example.jpg（手机拍摄的手抄报，带一块很硬的手影）：

• examples/SimdCodecs.AspNetCore：ASP.NET Core + SimdCodecs（ImageCodecs.Decode 加 ApplyOrientation 解码到一块 Rgba32 缓冲区并原地增强；上传文件有问题时直接返回解码器给出的错误原因），上传/拖拽图片、前后对比滑块、 auto / cpu 后端切换与耗时；POST /api/enhance 直接返回增强后的图片，API 文档在 /scalar。
• examples/SkiaSharp.Avalonia：跨平台桌面（Windows / Linux / macOS，Bgra32 的 SKBitmap），左右对比预览， 可切换 auto / cpu / vulkan（macOS 上为 metal），结果可存为 JPEG / PNG。
• examples/OpenCvSharp5.Wpf：WPF + OpenCvSharp5（Bgr24 的 Mat，按 Step() 传 stride），界面同上，支持拖拽。
• examples/PaddleOCR.Console：先用 SimdGcdrNet 增强，再用 SimdPaddleOCR 分别识别原图和增强图；两者共用同一块解码后的 RGBA 像素。默认图片 examples/ocr-example.jpg（取自 RealDAE） 背面透字严重：原图 OCR 出 56 行（大部分是背面透过来的乱码），增强后只剩正文的 14 行。

dotnet run --project examples/SimdCodecs.AspNetCore        # http://localhost:5190
dotnet run --project examples/SkiaSharp.Avalonia -- [图片]
dotnet run --project examples/OpenCvSharp5.Wpf -- [图片]
dotnet run --project examples/PaddleOCR.Console -- [图片] [输出.jpg]

本库不再自带 shader：所有 GPU 内核（包括 UpHead / ChannelShift 融合和像素 I/O）都在 Sdcb.SimdOnnx 里。

./tools/fetch-fixture.ps1                          # RealDAE 语料（约 36 MB）-> tests/testdata/realdae
dotnet test tests/Sdcb.SimdGcdrNet.Tests -c Release

golden 由 onnxruntime 对简化模型跑出（CPU 阈值 ≤1e-4 / Vulkan ≤5e-4）：仓库里只提交源图 {tag}_src.png 和两份 oracle 输出（_shadow.f32、_output.f32），GC-Net 输入、DR-Net 输入和最终 u8 图由 tests/GoldenDerive.cs 逐位一致地现算。重新生成用 dotnet run --project tools/GenGolden -- --models tests/testdata/models（纯 C#，OnnxRuntime oracle + SkiaSharp 解码）。

50 张 RealDAE 语料（NN_<color|shadow|bleed>.webp 及配对 NN_gt.webp 基准图）放在 sdcb/DocGainFixture，没下载时 CorpusTests 自动跳过； benchmark --corpus [cpu|vulkan|metal] 按图报耗时、MP/s、内存及对照 _gt 的 PSNR/MAE。

内核分发直接跟随 runtime 的 IsSupported 标志，ISA 档位用 runtime 开关强制降级： DOTNET_EnableAVX512=0 / DOTNET_EnableAVX512F=0（AVX2）、DOTNET_EnableAVX2=0（128 位 Vector）、 DOTNET_EnableAVX=0（SSE 无 FMA）、DOTNET_EnableHWIntrinsic=0（纯标量）。

CI（.github/workflows/test.yml） 两波并行，最后汇总成一份报告（显示在 run 的 Summary 页）：

• smoke（正确性）：win-x64、win-arm64、linux-x64、linux-arm64、osx-x64、osx-arm64（CPU 与 Metal）上跑 dotnet test 和语料冒烟（Benchmark --ci smoke：输出正常、两次运行一致、比输入更接近 GT；GPU 与 CPU 输出接近）， 另加 x64 上述各 ISA 档位与 arm64 纯标量；
• bench（性能）：Benchmark --ci bench 跑 20 张语料图、每个 case 多个 replica：win-x64（默认、无 AVX-512、 无 AVX2）、linux-x64、linux-arm64（NEON）、osx-arm64（CPU、Metal）。

支持 Native AOT（IsAotCompatible，裁剪 / AOT 无警告；CPU、Vulkan 输出与 JIT 逐字节一致）。x64 上可执行项目必须指定指令集， 否则 ILC 按 SSE 基线编译，Avx2.IsSupported / Avx512F.IsSupported 被折成 false，CPU 后端会静默退到 128 位 Vector<float> 档（慢约 1.3 倍）：

<IlcInstructionSet>x86-64-v3</IlcInstructionSet>   <!-- AVX2+FMA；x86-64-v4 才有 AVX-512 -->

这样编出的程序在不支持这些扩展的 CPU 上无法启动。arm64 不用设（NEON 在基线里）；GPU 后端不受影响。

推理引擎（Sdcb.SimdGcdrNet，即 src/Sdcb.SimdGcdrNet.Models 以外的全部代码）为 Apache-2.0； Sdcb.SimdGcdrNet.Models 沿用其内嵌的上游 GCDRNet 模型权重的 MIT 许可 （Copyright (c) 2024 Jiaxin Zhang），详见 THIRD-PARTY-NOTICES.txt（两个包内均附带）。 测试语料（sdcb/DocGainFixture）和 examples/ocr-example.jpg 取自同一论文的 RealDAE 数据集。