SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.02484 · 2019

Expert Sample Consensus Applied to Camera Re-Localization

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 2 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/1908.02484.json · badge: /api/ran/1908.02484.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
vislearn/esac canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
assert_size Ran
ran on a synthesized input
vislearn/esac/code/util.py
code served (permissive licence) · get_code("6a4dd75c868781a9")
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 tuple, ndim 5, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

# Create two tensors with 4D shape (batch, channels, height, width)
# coords1 has shape (2, 4, 5, 6) - batch=2, channels=4, height=5, width=6
coords1 = torch.randn(2, 4, 5, 6)

# coords2 has shape (2, 4, 5, 6) - same size for valid case
coords2 = torch.randn(2, 4, 5, 6)

ARGS = {
    "coords1": coords1,
    "coords2": coords2,
}
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 tuple, ndim 5, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
clamp_tensor Ran
ran on a synthesized input
vislearn/esac/code/util.py
code served (permissive licence) · get_code("b9b194e7bc7d3a9d")
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 Tensor, ndim 4, dtype family float, shape (2, 4, 6, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# coords1: should be a 4D tensor that will be sliced on dimensions 2 and 3
# The function accesses coords1[:, :, 0:coords2.size(2), 0:coords2.size(3)]
# So coords1 needs shape (batch, channels, height, width)
coords1 = torch.randn(2, 4, 10, 12)

# coords2: should be a 4D tensor where size(2) and size(3) are used as bounds
# The function calls coords2.size(2) and coords2.size(3)
# So coords2 needs shape (batch, channels, height, width)
coords2 = torch.randn(2, 4, 6, 8)

ARGS = {
    "coords1": coords1,
    "coords2": coords2,
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 6, 8) — shape (2, 4, 6, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
random_shift Not yet run
unverified (harvested, no recorded run)
vislearn/esac/code/util.py
code served (permissive licence) · get_code("4bccd3ca4e7be4e8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
random_shift 1 other paper
1 dated earlier
1905.04132 (2019-05)
Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Fitting model parameters to a set of noisy data points is a common problem in computer vision. In this work, we fit the 6D camera pose to a set of noisy correspondences between the 2D input image and a known 3D environment. We estimate these correspondences from the image using a neural network. Since the correspondences often contain outliers, we utilize a robust estimator such as Random Sample Consensus (RANSAC) or Differentiable RANSAC (DSAC) to fit the pose parameters. When the problem domain, e.g. the space of all 2D-3D correspondences, is large or ambiguous, a single network does not cover the domain well. Mixture of Experts (MoE) is a popular strategy to divide a problem domain among an ensemble of specialized networks, so called experts, where a gating network decides which expert is responsible for a given input. In this work, we introduce Expert Sample Consensus (ESAC), which integrates DSAC in a MoE. Our main technical contribution is an efficient method to train ESAC jointly and end-to-end. We demonstrate experimentally that ESAC handles two real-world problems better than competing methods, i.e. scalability and ambiguity. We apply ESAC to fitting simple geometric models to synthetic images, and to camera re-localization for difficult, real datasets.

For agents

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

get_harvested_code_for_paper("1908.02484")
get_code_for_paper("1908.02484")
have("1908.02484")

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

curl https://syntology.ai/api/ran/1908.02484.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.02484.svg)](https://syntology.ai/paper/1908.02484)

Connect an agent — have() is free.