Blame for README.md

---
library_name: "fastforks"
pipeline_tag: "image-to-3d"
license: "other"
license_name: "mit-code-weights-unstated"
license_link: "https://github.com/FangjinhuaWang/PatchmatchNet/blob/8dc6cb4/LICENSE"
tags:
- "multiview"
- "multi-view-stereo"
- "3d-reconstruction"
- "camera-pose-estimation"
- "cuda"
- "pytorch"
- "fastforks"
---
# PatchmatchNet (fastforks)

PatchmatchNet (Wang et al. 2021): learned PatchMatch multi-view stereo, the depth of a reference view from posed, calibrated source views and a depth search range. Three coarse-to-fine PatchMatch stages (random initialisation, adaptive propagation, group-wise correlation with pixel-wise view weights, adaptive spatial cost aggregation) on FPN features, then a depth refinement net at full resolution.

This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: <https://github.com/kleinicke/fastforks>. Kernels for the `kernels` backend: <https://huggingface.co/fastforks/kernels>. Original code: <https://github.com/FangjinhuaWang/PatchmatchNet> at `8dc6cb4`.

Task: multiview. Tier: experimental. Outputs: `depth`, `confidence`. Backends: `portable`, `kernels`.

Input: several images of one scene (posed and calibrated for multi-view stereo, unposed otherwise). Output: depth maps and, where the model predicts them, cameras and 3-D points.

## Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in [`card.toml`](https://github.com/kleinicke/fastforks/blob/main/src/fastforks/multiview/models/patchmatchnet/card.toml).

| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
| `patchmatchnet@1` | [params_000007.ckpt](https://github.com/FangjinhuaWang/PatchmatchNet/raw/8dc6cb40bdb7053e856598b378425c76a9dcf5e0/checkpoints/params_000007.ckpt) | `477b056c6235` | MIT (assumed from code) | yes |

## Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: MIT. Files: `LICENSE`.

Code licence: MIT; the authors do not state a separate weights licence.

Training data: DTU Robot Image Data Sets (MVS 2014) (The released checkpoint (checkpoints/params_000007.ckpt) is trained on DTU (README); the paper evaluates it zero-shot on Tanks and Temples and ETH3D).

- Licence note: The code is MIT; the checkpoint ships in the repository without a licence of its own (MIT assumed) and is trained on DTU, whose terms of use are not stated.

Licence evidence: https://github.com/FangjinhuaWang/PatchmatchNet/blob/8dc6cb4/LICENSE and README.md (the checkpoint ships in the repository)

## Input size

any H x W >= 5, resized or padded inside the model
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `patchmatchnet` 1988x2880 (7.9 GiB peak allocated, 9.4 reserved)

## Speed and memory

### Multiview, synthetic, 1536x1024

| model | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `patchmatchnet` | 248.06 | 219.74 | 201.66 | 29.57 | 7.4x | 6.8x | 1228 / 1272 | 1806 / 2096 | 740 / 856 |

### Startup and first call

| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
| --- | --- | --- | --- | --- | --- | --- |
| `patchmatchnet` | 0.04 (1536x1024) | 0.06 (1536x1024) | 0.05† (1536x1024) | 0.92 (1536x1024) | 0.25 (1536x1024) | 0.04 (1536x1024) |

### torch.compile and TensorRT

| model | input | portable ms | compile ms | compile s (cold) | TensorRT fp16 ms | ONNX + build s | kernels ms | peak MiB (alloc / reserved): portable | compile | TensorRT (device) |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `patchmatchnet` | 1536x1024 | 201.66 | 175.0 | 29.4 | 28.2 | 54 | 29.57 | 1806 / 2096 | 1798 / 1888 | 790 |

### Fixed-size speed and peak memory, all models

| model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
| --- | --- | --- | --- | --- | --- |
| `patchmatchnet` | portable | 43.1 ms / 439 / 522 | 154.4 ms / 1242 / 1534 | 408.6 ms / 2753 / 3346 | OOM |
| `patchmatchnet` | kernels | 9.2 ms / 253 / 328 | 24.4 ms / 693 / 942 | 56.7 ms / 1520 / 2016 | 378.6 ms / 8628 / 11332 |

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastforks/blob/main/docs/benchmarks.md) (RTX 5060 Ti 16 GB, sm_120). Original = the authors' code at the precision of portable (fp16, or `(fp32)` where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.

## Accuracy

### Parity with the original code

Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.5 % and p99 <= 3 % of the reference's median |value| (absolute error of the output `depth`).

## Usage

```python
from fastforks import multiview

model = multiview.load("patchmatchnet")  # mode="auto": the preferred backend from recorded measurements
result = model(["ref.jpg", "src1.jpg", "src2.jpg"], intrinsics=K, cam_to_world=c2w, depth_range=(0.5, 5.0))
result.depth  # [1, H, W] float32 tensor; views[0] = reference, K [N, 3, 3] pixels, c2w [N, 4, 4] OpenCV
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
```

Install with `pip install fastforks` (see <https://github.com/kleinicke/fastforks>). Other variants: `patchmatchnet`.

## Kernels backend

`multiview.load("patchmatchnet", mode="kernels")` runs our CUDA kernels (`patchmatchnet`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.

<!-- staged from fastforks 7204e33f (2026-11-05) -->