SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.19174 · CVPR · 2024

XFeat: Accelerated Features for Lightweight Image Matching

Guilherme Potje, Renato Martins, Felipe Cadar, Erickson Nascimento, André Araujo

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.19174.json · badge: /api/ran/2404.19174.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
verlab/accelerated_features community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
InterpolateSparse2d Ran
ran on a synthesized input · constructed an object; no result was computed
verlab/accelerated_features/modules/xfeat.py
code served (permissive licence) · get_code("35fc848f2872c2e8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, InterpolateSparse2d: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple InterpolateSparse2d instance to use as the model
class InterpolateSparse2d(nn.Module):
    """ Efficiently interpolate tensor at given sparse 2D positions. """

    def __init__(self, mode='bicubic', align_corners=False):
        super().__init__()
        self.mode = mode
        self.align_corners = align_corners

    def normgrid(self, x, H, W):
        """ Normalize coords to [-1,1]. """
        return 2.0 * (x / torch.tensor([W - 1, H - 1], device=x.device, dtype=x.dtype)) - 1.0

    def forward(self, x, pos, H, W):
        """
        Input
            x: [B, C, H, W] feature tensor
            pos: [B, N, 2] tensor of positions
            H, W: int, original resolution of input 2d positions -- used in normalization [-1,1]

        Returns
            [B, N, C] sampled channels at 2d positions
        """
        import torch.nn.functional as F
        grid = self.normgrid(pos, H, W).unsqueeze(-2).to(x.dtype)
        x = F.grid_sample(x, grid, mode=self.mode, align_corners=False)
        return x.permute(0, 2, 3, 1).squeeze(-2)

# Create instance and prepare arguments for forward pass
interpolate_module = InterpolateSparse2d(mode='bicubic', align_corners=False)

# Setup tensor arguments for forward pass
B, C, H, W = 2, 4, 8, 6  # batch=2, channels=4, height=8, width=6
N = 3  # number of sparse positions

x = torch.randn(B, C, H, W)  # [B, C, H, W] feature tensor
pos = torch.rand(B, N, 2) * torch.tensor([W - 1, H - 1], dtype=torch.float32)  # [B, N, 2] positions
H_orig = H  # original height for normalization
W_orig = W  # original width for normalization

ARGS = {
    'mode': 'bicubic',
    'align_corners': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type InterpolateSparse2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a InterpolateSparse2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
XFeat Not yet run
unverified (harvested, no recorded run)
verlab/accelerated_features/modules/xfeat.py
code served (permissive licence) · get_code("b3d69fb9c383a9cc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting, extracting, and matching local features. Our new model satisfies a critical need for fast and robust algorithms suitable to resource-limited devices. In particular, accurate image matching requires sufficiently large image resolutions -for this reason, we keep the resolution as large as possible while limiting the number of channels in the network. Besides, our model is designed to offer the choice of matching at the sparse or semi-dense levels, each of which may be more suitable for different downstream applications, such as visual navigation and augmented reality. Our model is the first to offer semi-dense matching efficiently, leveraging a novel match refinement module that relies on coarse local descriptors. XFeat is versatile and hardwareindependent, surpassing current deep learning-based local features in speed (up to 5x faster) with comparable or better accuracy, proven in pose estimation and visual localization. We showcase it running in real-time on an inexpensive laptop CPU without specialized hardware optimizations. Code and weights are available at verlab.dcc.ufmg.br/ descriptors/xfeat_cvpr24.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.19174")
get_code_for_paper("2404.19174")
have("2404.19174")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.19174.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.19174.svg)](https://syntology.ai/paper/2404.19174)

Connect an agent — have() is free.