SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.01710 · CVPR · 2021

Learning Accurate Dense Correspondences and When to Trust Them

Radu Timofte, Prune Truong, Van Gool, Martin Luc

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2101.01710.json · badge: /api/ran/2101.01710.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
google-research/sparf community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
flow_net_model_select Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
google-research/sparf/source/models/flow_net.py
code served (permissive licence) · get_code("f745dff886f4ce2c")
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) and returned SPSGInference. 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)

# The function only uses the backbone parameter to select which model to instantiate
# and the train_features parameter to pass to the model constructor.
# Since the function imports from third_party modules that won't exist,
# we'll use the 'SPSG' branch which has a simpler import path that we can mock.

# Create a mock for SPSGInference since we can't import the real one
class SPSGInference(nn.Module):
    def __init__(self):
        super().__init__()
    
    def forward(self, x):
        return x

# Mock the module path
import sys
from types import ModuleType

# Create mock modules for the import path
spsg_matcher = ModuleType('spsg_matcher')
superglue_module = ModuleType('superglue_module')
superglue_module.SPSGInference = SPSGInference

spsg_matcher.superglue_module = superglue_module

source = ModuleType('source')
utils = ModuleType('utils')
utils.spsg_matcher = spsg_matcher

source.utils = utils

sys.modules['source'] = source
sys.modules['source.utils'] = utils
sys.modules['source.utils.spsg_matcher'] = spsg_matcher
sys.modules['source.utils.spsg_matcher.superglue_module'] = superglue_module

ARGS = {
    'backbone': 'SPSG',
    'train_features': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
source, third_party, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SPSGInference — a SPSGInference output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SPSGInference 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Establishing dense correspondences between a pair of images is an important and general problem. However, dense flow estimation is often inaccurate in the case of large displacements or homogeneous regions. For most applications and down-stream tasks, such as pose estimation, image manipulation, or 3D reconstruction, it is crucial to know when and where to trust the estimated matches. In this work, we aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map indicating the reliability and accuracy of the prediction. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. In particular, we parametrize the predictive distribution as a constrained mixture model, ensuring better modelling of both accurate flow predictions and outliers. Moreover, we develop an architecture and training strategy tailored for robust and generalizable uncertainty prediction in the context of self-supervised training. Our approach obtains stateof-the-art results on multiple challenging geometric matching and optical flow datasets. We further validate the usefulness of our probabilistic confidence estimation for the task of pose estimation. Code and models are available at https://github.com/PruneTruong/PDCNet.

For agents

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

get_harvested_code_for_paper("2101.01710")
get_code_for_paper("2101.01710")
have("2101.01710")

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

curl https://syntology.ai/api/ran/2101.01710.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.01710.svg)](https://syntology.ai/paper/2101.01710)

Connect an agent — have() is free.