SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.06504 · 2019

Visual-Inertial Mapping with Non-Linear Factor Recovery

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 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 3 have no contract verdict; 3 failures of our instrument; 5 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/1904.06504.json · badge: /api/ran/1904.06504.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
VladyslavUsenko/basalt-headers-mirror community (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
minxuanjun/basalt_class community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
Vector2 Ran
ran; our contract draft was wrong, not the code
minxuanjun/basalt_class/thirdparty/basalt-headers/thirdparty/Sophus/py/sophus/matrix.py
code served (permissive licence) · get_code("3fb6584cf4dc0220")
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 MutableDenseMatrix. 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 sympy

torch_seed = 0

ARGS = {
    "x": 5,
    "y": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sympy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MutableDenseMatrix — a MutableDenseMatrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MutableDenseMatrix output the recorded ndim 2 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
cse_as_cxx Ran
ran on a synthesized input
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_jacobians.py
code served (permissive licence) · get_code("7df6e4cd3c9216f9")
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 str. 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 numpy as np
from sympy import symbols, sin, cos, exp, simplify
from sympy.utilities.lambdify import lambdify

# Create symbolic variables
x, y, z = symbols('x y z')

# Create some symbolic expressions
expr1 = sin(x) * cos(y)
expr2 = exp(z) + x**2
expr3 = (x + y) * (x - y)

# Create a CSE tuple: (subexprs, rhss)
# subexprs is a list of (variable_symbol, expression) tuples
# rhss is a list of expressions representing the right-hand sides
subexprs = [
    (symbols('t0'), x + y),
    (symbols('t1'), x - y),
    (symbols('t2'), sin(x)),
]

rhss = [
    symbols('t0') * symbols('t1'),
    symbols('t2') * cos(y),
    exp(z) + x**2,
]

cse_tuple = (subexprs, rhss)

# Create expression names for the output variables
expr_names = ['result0', 'result1', 'result2']

ARGS = {
    'cse_tuple': cse_tuple,
    'expr_names': expr_names,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sympy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
dot Ran
ran; our contract draft was wrong, not the code
minxuanjun/basalt_class/thirdparty/basalt-headers/thirdparty/Sophus/py/sophus/matrix.py
code served (permissive licence) · get_code("27d2ed826241f29f")
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 Integer. 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 sympy

# Create two sympy matrices for the dot product function
# The function iterates through columns and rows, multiplying corresponding elements
# and summing them up. This is essentially a Frobenius inner product.

# Create matrices of distinct sizes to allow shape probing
left_matrix = sympy.Matrix([
    [1, 2, 3],
    [4, 5, 6],
    [7, 8, 9],
    [10, 11, 12]
])

right_matrix = sympy.Matrix([
    [2, 3, 4],
    [5, 6, 7],
    [8, 9, 10],
    [11, 12, 13]
])

ARGS = {
    "left": left_matrix,
    "right": right_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sympy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Integer — a Integer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Integer 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
numeric_J_f_from_xy Ran
ran on a synthesized input
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_compute_rpmax.py
code served (permissive licence) · get_code("e8b20f856e5b2566")
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 function. 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 numpy as np

# Define a simple function f that takes a 2D point [x, y] and returns a scalar
# The function uses both x and y coordinates
def f(xy):
    """
    A simple test function: f(x, y) = x^2 + 2*y
    This will be differentiated numerically.
    """
    x, y = xy[0], xy[1]
    return x**2 + 2*y

ARGS = {
    "f": f
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
squared_norm Ran
ran; our contract draft was wrong, not the code
minxuanjun/basalt_class/thirdparty/basalt-headers/thirdparty/Sophus/py/sophus/matrix.py
code served (permissive licence) · get_code("8e30df616b00e951")
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 Integer. 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 sympy

# Create two small sympy matrices for testing
# Using distinct dimensions (2x3 and 2x3) to match what squared_norm expects
matrix1 = sympy.Matrix([
    [1, 2, 3],
    [4, 5, 6]
])

# For squared_norm, we need a single matrix argument
# squared_norm computes dot(m, m), so we need one matrix
test_matrix = sympy.Matrix([
    [1, 2],
    [3, 4],
    [5, 6]
])

ARGS = {
    "m": test_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sympy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Integer — a Integer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Integer 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
test_point_inyective Ran
ran on a synthesized input
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_test_points.py
code served (permissive licence) · get_code("96295c855c9e8f08")
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 bool, ndim 0, dtype family float, shape () 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 numpy as np

class MockMutation:
    """Mock mutation object with project and unproject methods."""
    
    def __init__(self):
        self.__name__ = "MockMutation"
    
    def project(self, x, y, z):
        """Project 3D point to 2D."""
        # Simple stereographic projection-like mapping
        if z != 0:
            mu = x / z
            mv = y / z
        else:
            mu, mv = 0.0, 0.0
        return mu, mv
    
    def unproject(self, mu, mv, N=None, eps=None):
        """Unproject 2D point back to 3D unit vector."""
        # Reverse of project: reconstruct normalized 3D point
        rho_sq = mu**2 + mv**2
        norm_val = np.sqrt(rho_sq + 1.0)
        mx = mu / norm_val
        my = mv / norm_val
        mz = 1.0 / norm_val
        return mx, my, mz

mut = MockMutation()

ARGS = {
    "x": 0.5,
    "y": 0.3,
    "z": 0.8,
    "rpmax": 2.0,
    "mut": mut,
    "N": None,
    "eps": 1e-6,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () 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
cse_codegen Not yet run
unverified (harvested, no recorded run)
minxuanjun/basalt_class/thirdparty/basalt-headers/thirdparty/Sophus/py/sophus/cse_codegen.py
code served (permissive licence) · get_code("bcddb9f81acc6e7a")
How it ran

no invocation recorded.

distort_symbolic Not yet run
unverified (harvested, no recorded run)
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_jacobians.py
code served (permissive licence) · get_code("fbca7d1bafd2f67f")
How it ran

no invocation recorded.

my_least_squares Not yet run
unverified (harvested, no recorded run)
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_compute_rpmax.py
code served (permissive licence) · get_code("0217fe5140cc51c7")
How it ran

no invocation recorded.

my_least_squares_old Not yet run
unverified (harvested, no recorded run)
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_compute_rpmax.py
code served (permissive licence) · get_code("9c1d9a0899486422")
How it ran

no invocation recorded.

project_symbolic Not yet run
unverified (harvested, no recorded run)
VladyslavUsenko/basalt-headers-mirror/python/radtan8/main_jacobians.py
code served (permissive licence) · get_code("02ed0223995b4028")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 7 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
Vector2 2 other papers
2 later
2311.16728 (2023-11)
Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
2409.07365 (2024-09)
Event-based Mosaicing Bundle Adjustment
cse_codegen 2 other papers
2 later
2311.16728 (2023-11)
Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
2409.07365 (2024-09)
Event-based Mosaicing Bundle Adjustment
dot 2 other papers
2 later
2311.16728 (2023-11)
Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
2409.07365 (2024-09)
Event-based Mosaicing Bundle Adjustment
squared_norm 2 other papers
2 later
2311.16728 (2023-11)
Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras
2409.07365 (2024-09)
Event-based Mosaicing Bundle Adjustment

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

Cameras and inertial measurement units are complementary sensors for ego-motion estimation and environment mapping. Their combination makes visual-inertial odometry (VIO) systems more accurate and robust. For globally consistent mapping, however, combining visual and inertial information is not straightforward. To estimate the motion and geometry with a set of images large baselines are required. Because of that, most systems operate on keyframes that have large time intervals between each other. Inertial data on the other hand quickly degrades with the duration of the intervals and after several seconds of integration, it typically contains only little useful information. In this paper, we propose to extract relevant information for visual-inertial mapping from visual-inertial odometry using non-linear factor recovery. We reconstruct a set of non-linear factors that make an optimal approximation of the information on the trajectory accumulated by VIO. To obtain a globally consistent map we combine these factors with loop-closing constraints using bundle adjustment. The VIO factors make the roll and pitch angles of the global map observable, and improve the robustness and the accuracy of the mapping. In experiments on a public benchmark, we demonstrate superior performance of our method over the state-of-the-art approaches.

For agents

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

get_harvested_code_for_paper("1904.06504")
get_code_for_paper("1904.06504")
have("1904.06504")

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

curl https://syntology.ai/api/ran/1904.06504.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.06504.svg)](https://syntology.ai/paper/1904.06504)

Connect an agent — have() is free.