LightGlue (fastforks)

LightGlue (Lindenberger, Sarlin and Pollefeys 2023): sparse feature matching. A keypoint detector-descriptor (ALIKED or DISK) finds up to 2048 keypoints per image at a 1024-pixel long side, and a transformer with self- and cross-attention, adaptive depth and point pruning matches them. Returns both keypoint sets, the index pairs of the matches and their confidence.

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/cvg/LightGlue at 5a650c444718.

Task: matching. Tier: experimental. Outputs: keypoints1, keypoints2, pairs, scores. Backends: portable, kernels.

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. 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.

Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.

variant weights (author link) SHA-256 weights licence commercial use
aliked-lightglue@1 aliked_lightglue.pth
aliked-n16.pth
d975e965b105
5be8704840ed
Apache-2.0 AND BSD-3-Clause yes
disk-lightglue@1 disk_lightglue.pth
depth-save.pth
b5b21d47ea24
9c2ee4ded238
Apache-2.0 AND BSD-3-Clause yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0 AND BSD-3-Clause. Licence files: LICENSE, LICENSE-ALIKED.

Training data: MegaDepth (Internet photo collections with SfM / MVS depth) (LightGlue: pretrained on synthetic homographies of the Oxford-Paris 1M distractor images (Flickr; no dataset entry here), fine-tuned on MegaDepth. ALIKED and DISK: trained on MegaDepth.).

Licence evidence: https://github.com/cvg/LightGlue/blob/5a650c444718caffc2669dc0094cde908f42dd73/README.md#license ; https://github.com/Shiaoming/ALIKED/blob/683d7c65197395c0b3f01ebe76e1084a27e73a65/LICENSE ; https://github.com/cvlab-epfl/disk/blob/8dc6d4d65b47210f629e21ad1fbfb56944b11696/LICENSE.txt

Input size

any H x W >= 32, padded to a multiple of 32 Tested up to (portable, fp16, RTX 5060 Ti 16 GB): aliked-lightglue 3000x4000 (1.5 GiB peak allocated, 2.0 reserved); disk-lightglue 3000x4000 (2.2 GiB peak allocated, 2.9 reserved)

Speed and memory

Matching, synthetic, 768x1024

model time (ms): original fp32 original portable kernels kernels speed-up: vs original vs portable peak memory (MiB, allocated / reserved): original portable kernels
aliked-lightglue – 41.8 40.6 35.1 1.2x 1.2x 1305 / 1364 1300 / 1404 1238 / 1324
disk-lightglue – 117 116 52.1 2.2x 2.2x 1955 / 2412 1950 / 2398 736 / 778

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
aliked-lightglue 1.49 0.17 1.46 0.73 0.79 0.90
disk-lightglue 1.43 0.20 0.57 0.64 0.63 0.30

torch.compile and TensorRT

model input time: portable compile TensorRT fp16 kernels preparation: compile (cold first call) ONNX + engine build peak MiB (alloc / reserved): portable compile kernels TensorRT (engine + torch)
aliked-lightglue 768x1024 40.6 ms 29.5 ms planned for 0.2.1 35.1 ms 30.8 s – 1300 / 1404 1653 / 1680 1238 / 1324 –
disk-lightglue 768x1024 116 ms 113 ms planned for 0.2.1 52.1 ms 21.4 s – 1950 / 2398 1375 / 1502 736 / 778 –

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

Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above 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

On public datasets

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.

variant dataset original fp32 original fp16 portable kernels note
aliked-lightglue MegaDepth-1500, relative pose AUC@5 / @10 / @20 degrees 50.7 / 67.6 / 80.0
aliked-lightglue MegaDepth-1500, every 5th pair, relative pose AUC@5 / @10 / @20 degrees 51.7 / 68.2 / 81.0 51.4 / 68.8 / 80.8 52.1 / 69.2 / 81.4 51.0 / 68.3 / 80.9
disk-lightglue MegaDepth-1500, every 5th pair, relative pose AUC@5 / @10 / @20 degrees 45.6 / 63.3 / 77.3 44.9 / 63.4 / 77.0 45.6 / 63.3 / 77.3 45.0 / 62.9 / 76.6

Measured on portable: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks ec7b1307+port/p1-match, 2026-11-12; kernels: NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks ecac19a2-dirty, 2026-11-15.

Parity with the original code

Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 3e-05 vs the original. GPU, portable float32 and kernels float16 (the defaults): mean |diff| <= 0.0052 and p99 <= 0.012 (absolute error of the output keypoints1).

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 counts are data-dependent (torch.compile runs with graph breaks; ONNX / TensorRT export fails).

Usage

from fastforks import matching

model = matching.load("aliked-lightglue")  # mode="auto": the preferred backend from recorded measurements
result = model("view1.jpg", "view2.jpg")
result.keypoints1, result.keypoints2, result.pairs  # [N, 2], [M, 2] pixels; [K, 2] int64 index pairs
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: aliked-lightglue, disk-lightglue.

Kernels backend

matching.load("aliked-lightglue", mode="kernels") runs our CUDA kernels (igev, cutlass_conv, cudnn_hacc). 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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including fastforks/lightglue