Models · Dense matching

FlexGlue

FlexGlue (ETH Zurich and partners, 2026): sparse matching of two photos of one scene: ALIKED keypoints, DINOv3 ConvNeXt features and a transformer that predicts where each keypoint lands in the other photo; keypoint index pairs. MIT; DINOv3 backbone weights under the DINOv3 licence.

experimental Fork of cvg/FlexGlue@9992029 · backends: portable, kernels

Checkpoint aliked-flexglue

Paper 2026 Added in 0.2.0 Evaluated with 0.2.0

Portable, RTX 5060 Ti 16 GB 129 ms 768x1024, fp16
vs the faster original 2.7× original fp32: 348 ms
Peak memory 1,775 MiB original: 1,801 MiB
Accuracy vs original fp32 +2.5 portable AUC@5°, MegaDepth-1500 (50.8 original)

Use it

pip install fastforks

Lean install with only what this model needs: pip install fastforks-core

from fastforks import matching

model = matching.load("aliked-flexglue")  # kernels on a supported GPU, else portable PyTorch
result = model(image_a, image_b)
result.keypoints1  # also: keypoints2, pairs, scores
result.backend  # what ran: mode, device, dtype, kernels

points1, points2 = result.matches(5000)  # matched pixels, sampled where the model is certain
pose = matching.estimate_pose(points1, points2, K1, K2)  # relative pose on the GPU (RANSAC); K = intrinsics [3, 3]
pose.R, pose.t, pose.inliers  # rotation, unit translation, inlier mask
fastforks bench aliked-flexglue

Times the model on this machine. load(…, mode="portable") or mode="kernels" picks a backend; usage guide.

Speed and memory

Every backend on one GPU (RTX 5060 Ti 16 GB) and the same input, the authors’ code included. Kernels runs fp16. Portable runs fp16 on CUDA.

Input: synthetic, 768x1024 (the task’s standard size)

BackenddtypeTime per call (ms)vs original fp16Peak memory
allocated / reserved
Load (s)First call (s)
Original fp32fp32not measured ––––
Original (own default)upstream FlexGlue(mp=None).match_pair(sparse=True) + ALIKED(origin=corner), 2048 keypointsfp32 348–1,801 MiB/1,892 MiB4.51.66
Portable fp32fp32not measured ––––
Portablefp16 1292.7×1,775 MiB/1,886 MiB0.91.20
Kernelsnot measured ––––
Portable + torch.compile 96.13.6×1,762 MiB/1,826 MiB79 (build)–
TensorRTONNX export: torch.export failedfails––––

Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-15. First call, 3 warm-up, peak reset, median of 3 rounds x median of 5. Ratios divide two times of this table (same GPU, same input). Original fp16 is the authors’ own precision option, else torch.autocast. torch.compile and TensorRT: build time instead of load time. TensorRT memory (engine, not comparable) is the GPU memory the engine took, read from the driver because TensorRT allocates outside PyTorch, so it can't be compared with the PyTorch peaks of the other rows.

Other devices

DeviceBackenddtypems / callPeak memoryOutput vs referenceInput
Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-17Portablefp161069 3,088 MiB processskip768x1024
Portablefp321124 3,932 MiB processskip768x1024
Kernelsfp32not implemented–768x1024

CUDA memory is torch’s peak allocated / reserved; Apple has no such counter, so the Mac rows show the process footprint (weights, Python and torch included). “Output vs reference” compares the device’s output with the stored golden output under the card’s tolerance; – = not checked on that device. Kernels “not implemented” = no kernels for this model on that backend yet: it runs portable there.

Licence and weights

Commercial use allowed

Code
MIT AND BSD-3-Clause LICENSELICENSE-ALIKEDLICENSE-DINOv3
Weights
MIT AND LicenseRef-DINOv3-License AND BSD-3-Clause source
Training data
FlexGlue: the README states no training data and the training code is not released (see the paper). The DINOv3 ConvNeXt-B backbone was pretrained on LVD-1689M (Meta, not released); ALIKED was trained on MegaDepth.
  • The checkpoint includes the DINOv3 ConvNeXt-B backbone weights (`extractor.backbone.*`): the DINOv3 License (Meta: attribution and conditions apply) covers them; read it before commercial use.

Our reading of the licences, not legal advice.

Weights

flexglue.pth 567 MB· hosted on GitHub
aliked-n16.pth 2.7 MB· hosted on raw.githubusercontent.com

fastforks downloads and checks these files on first use (fastforks download aliked-flexglue).

Accuracy

The test set through the authors’ code and through ours: same checkpoint, same protocol. The distance between the original’s fp32 and fp16 runs is what half precision alone costs; our runs should stay within it.

MegaDepth-1500

every 5th pair, relative pose AUC@5 / @10 / @20 degrees

RundtypeAUC@5° ↑AUC@10° ↑AUC@20° ↑Δ AUC@5° vs fp32 originalpairsms / pair
Original fp32fp3250.868.280.4 reference 300 353
Original fp16not measured
Portable fp32fp3252.869.681.7 +2.0 300 397
Portablefp1653.370.182.0 +2.5 300 181
Kernelsnot measured

Dense matchers: 5000 matches per pair sampled from the warp by certainty (upstream's balanced KDE sampling); sparse matchers: all their matches of one call (LightGlue, XFeat: LightGlue's MegaDepth-1500 setting; LoFTR, DeDoDe: their card defaults). OpenCV essential-matrix RANSAC (0.5 px threshold, normalised by the mean focal length); AUC of the larger of the rotation and translation-direction errors. The same 300 pairs for all modes, so float32 and bfloat16 compare pair for pair. Original = the authors’ code, same checkpoint and protocol. Measured on original fp32: RTX 5060 Ti, torch 2.14.1+cu130, 2026-11-16; portable fp32: RTX 5060 Ti, torch 2.14.1+cu130, fastforks d073b335, 2026-11-17; portable: RTX 5060 Ti, torch 2.14.1+cu130, fastforks 68b2f345, 2026-11-16.

Relative pose on the GPU

A dense matcher is usually followed by RANSAC on its matches to get the camera motion. fastforks does that step on the GPU too: result.matches(n) samples matched points where the model is certain, and matching.estimate_pose runs essential-matrix RANSAC on them, many image pairs per call, with no copy to the CPU. Like the models it has a portable (plain PyTorch) and a kernels (CUDA) backend.

SolverRuns onThreshold (px)Pose AUC@5 / @10 / @20Pairs per second
fastforks estimate_pose, kernelsGPU, batches of 500 pairs1.069.9 / 81.5 / 89.318,446
fastforks estimate_pose, portableGPU, batches of 500 pairs1.069.6 / 81.2 / 89.1418
PoseLib 2.0.5CPU, 16 processes1.070.0 / 81.6 / 89.5325
OpenCV USAC (MAGSAC++)CPU, 16 processes0.565.7 / 78.6 / 87.3271
OpenCV RANSACCPU, 16 processes0.562.9 / 76.9 / 86.4323

MegaDepth-1500, RoMa v2 matches (5000 per pair), 5 samplings, the same matches for every solver, on one machine: RTX 5060 Ti and a Ryzen 7 5800X (16 threads). Each solver runs at the inlier threshold where it is most accurate. Pairs per second is wall-clock throughput over all 7500 poses: the CPU solvers run one pair per call in 16 single-threaded processes, the GPU solver takes 500 pairs per call. One pair alone takes about 1.7 ms with the kernels, 29 ms with PoseLib and 24 ms with OpenCV RANSAC on one core. The accuracy table above stays on OpenCV RANSAC, as in the papers, so it is comparable with published numbers; this table is the only place the GPU solver is used.

Closeness to the original

Beyond the test-set scores: the raw output of ours against the original’s fp32 output on the same input, pixel by pixel. CPU, float32: max |diff| <= 0.0001 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0052 and p99 <= 0.012 (absolute error of the output keypoints1).

CheckToleranceMeasured
CPU fp32, max |diff|≤ 0.0001 not recorded
cpu_min_recall≤ 0.99 not recorded
cpu_min_match≤ 0.99 not recorded
GPU default dtypes, mean |diff|≤ 0.0052 0.00118
GPU default dtypes, p99 |diff|≤ 0.012 0.00319
gpu_min_recall≤ 0.99 not recorded
gpu_min_match≤ 0.98 not recorded

Recorded for aliked-flexglue on RTX 5060 Ti, torch 2.10.0+cu130, 2026-11-17, with these kernels: image_normalize

Details

FlexGlue (Lindenberger, Sarlin, Miksik and Pollefeys 2026): sparse feature matching from dense features. ALIKED finds up to 2048 keypoints per image at a 1024-pixel long side, a DINOv3 ConvNeXt-B describes each image at 512 x 512, nine transformer layers (rotary self-attention, cross-attention) relate both feature maps, and a head predicts where each keypoint lands in the other image; mutual nearest neighbours of keypoints and predictions are the matches. Returns both keypoint sets, the index pairs of the matches and their confidence.

Input / output
Input: two RGB images of one scene. Output: for every pixel of the first image its position in the second (x, y in pixels) and a certainty that the pixel is visible in both.
What the numbers mean, and which models need the camera focal length

Sparse matchers (LightGlue) return the keypoints of both images and the index pairs of the matched ones instead. To reconstruct camera poses from an image folder with these matchers, see [structure from motion](../sfm.md).

Input size
any H x W >= 32, padded to a multiple of 32; tested up to 3000x4000 (2,039 MiB allocated)
Options
  • max_keypoints=2048>= 1· changes the output
  • long_side=1024>= 0· changes the output
  • size=512>= 32· changes the output
Outputs
keypoints1, keypoints2, pairs, scores
CUDA kernels
  • image_normalize
Apple (MPS)
fp32, fp16

Limitations

  • Sparse output: no dense warp. `result.matches()` gives the matched points for `estimate_pose`; `pairs` are the index pairs pycolmap / COLMAP databases take.
  • One image pair per call internally (batches run pair by pair); the keypoint counts differ per image.
  • No exportable module: the keypoint and match counts are data-dependent (`torch.compile` runs with graph breaks; ONNX / TensorRT export fails).
  • Upstream's sparse mode only: no RoMa v2 refiner, no dense or sampled matches and no covisibility score.
  • Two resizes per image as upstream: ALIKED sees a long side of `long_side` (aspect kept), the descriptor a `size` x `size` square whatever the aspect ratio.
Full reference, generated from the repository

FlexGlue (ETH Zurich and partners, 2026): sparse matching of two photos of one scene: ALIKED keypoints, DINOv3 ConvNeXt features and a transformer that predicts where each keypoint lands in the other photo; keypoint index pairs. MIT; DINOv3 backbone weights under the DINOv3 licence.

Commercial use: yes.

variantinputbackendtime (ms)peak memory (MiB, allocated / reserved)
aliked-flexgluesynthetic (768x1024)original
portable
kernels
portable + torch.compile
TensorRT fp16
348
129
–
96.1
fails: ONNX export: torch.export failed
1801 / 1892
1775 / 1886
–
1762 / 1826
–
Details
  • Original code: https://github.com/cvg/FlexGlue at 99920296d082
  • Code licence: MIT AND BSD-3-Clause (permissive); files: LICENSE, LICENSE-ALIKED, LICENSE-DINOv3
  • Weights licence: MIT AND LicenseRef-DINOv3-License AND BSD-3-Clause
  • Licence evidence: https://github.com/cvg/FlexGlue/blob/99920296d082c9405ebfd612d674efe288e74881/README.md#license ; https://github.com/Shiaoming/ALIKED/blob/683d7c65197395c0b3f01ebe76e1084a27e73a65/LICENSE
  • Training data: FlexGlue: the README states no training data and the training code is not released (see the paper). The DINOv3 ConvNeXt-B backbone was pretrained on LVD-1689M (Meta, not released); ALIKED was trained on MegaDepth.
  • Licence note: The checkpoint includes the DINOv3 ConvNeXt-B backbone weights (extractor.backbone.*): the DINOv3 License (Meta: attribution and conditions apply) covers them; read it before commercial use.
  • Options: max_keypoints = 2048 (>= 1), long_side = 1024 (>= 0), size = 512 (>= 32)
  • Kernel libraries: image_normalize
  • Variants: aliked-flexglue
  • Outputs: keypoints1, keypoints2, pairs, scores
  • Input size: any H x W >= 32, padded to a multiple of 32
  • Tested up to (portable, fp16, RTX 5060 Ti 16 GB): aliked-flexglue 3000x4000 (2.0 GiB peak allocated, 2.5 reserved)
  • aliked-flexglue 768x1024, first call: portable + torch.compile 79 s (cold Inductor cache).
  • aliked-flexglue original 768x1024: upstream FlexGlue(mp=None).match_pair(sparse=True) + ALIKED(origin=corner), 2048 keypoints
  • aliked-flexglue load / first call: original 4.5 s / 1.661 s, portable 0.92 s / 1.199 s
  • Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5

Measured

Dense matchers: 5000 matches per pair sampled from the warp by certainty (upstream's balanced KDE sampling); sparse matchers: all their matches of one call (LightGlue, XFeat: LightGlue's MegaDepth-1500 setting; LoFTR, DeDoDe: their card defaults). OpenCV essential-matrix RANSAC (0.5 px threshold, normalised by the mean focal length); AUC of the larger of the rotation and translation-direction errors. The same 300 pairs for all modes, so float32 and bfloat16 compare pair for pair. Original = the original code named under Details, same checkpoint and protocol.

variantdatasetoriginal fp32portableportable fp32note
aliked-flexglueMegaDepth-1500, every 5th pair, relative pose AUC@5 / @10 / @20 degrees50.8 / 68.2 / 80.453.3 / 70.1 / 82.052.8 / 69.6 / 81.7

Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 68b2f345, 2026-11-16; portable32: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks d073b335, 2026-11-17.

Parity

CPU, float32: max |diff| <= 0.0001 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0052 and p99 <= 0.012 (absolute error of the output keypoints1).

variantkernels error vs original, mean / p99GPU, torchkernels used
aliked-flexglue0.00118 / 0.00319RTX 5060 Ti, torch 2.10.0+cu130image_normalize@592f5511307a:sm_120

Limitations

  • Sparse output: no dense warp. result.matches() gives the matched points for estimate_pose; pairs are the index pairs pycolmap / COLMAP databases take.
  • One image pair per call internally (batches run pair by pair); the keypoint counts differ per image.
  • No exportable module: the keypoint and match counts are data-dependent (torch.compile runs with graph breaks; ONNX / TensorRT export fails).
  • Upstream's sparse mode only: no RoMa v2 refiner, no dense or sampled matches and no covisibility score.
  • Two resizes per image as upstream: ALIKED sees a long side of long_side (aspect kept), the descriptor a size x size square whatever the aspect ratio.

Example output

No example rendered for this checkpoint yet.