SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.01654 · ECCV · 2024

Deep Patch Visual SLAM

Jia Deng, Lahav Lipson, Zachary Teed

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2408.01654.json · badge: /api/ran/2408.01654.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
princeton-vl/dpvo canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
coords_grid Ran
ran, honoured the contract we drafted
princeton-vl/dpvo/dpvo/projective_ops.py
code served (permissive licence) · get_code("0cc157cee30b6b04")
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 3, dtype family float, shape (4, 3, 2) 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)

# The function coords_grid takes:
# - ht: height (int)
# - wd: width (int)
# - **kwargs: passed to .to() method, typically device and dtype specs

ARGS = {
    "ht": 4,
    "wd": 3,
}
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 3, dtype family float, shape (4, 3, 2) — shape (4, 3, 2) 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
coords_grid Ran
ran, honoured the contract we drafted
princeton-vl/dpvo/dpvo/utils.py
code served (permissive licence) · get_code("30b7221cea33a5cc")
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 5, dtype family float, shape (2, 3, 2, 4, 5) 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)

ARGS = {
    'b': 2,
    'n': 3,
    'h': 4,
    'w': 5,
}
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 5, dtype family float, shape (2, 3, 2, 4, 5) — shape (2, 3, 2, 4, 5) 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
coords_grid_with_index Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
princeton-vl/dpvo/dpvo/utils.py
code served (permissive licence) · get_code("a94e2de14f27d6be")
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. 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

torch.manual_seed(0)

# Create a small tensor with shape (batch=2, num_frames=3, height=4, width=5)
d = torch.randn(2, 3, 4, 5)

ARGS = {
    "d": d,
}
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 — a tuple output has no array shape of its own; none is 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
extract_intrinsics Ran
ran; our contract draft was wrong, not the code
princeton-vl/dpvo/dpvo/projective_ops.py
code served (permissive licence) · get_code("b89d818f78edbb63")
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 4, 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)

# The function expects intrinsics to be a tensor that supports:
# - indexing with [..., None, None, :]
# - .unbind(dim=-1) method
# This suggests a tensor of shape (..., num_intrinsics)
# We'll create a small batch of intrinsic parameters

intrinsics = torch.randn(2, 4)

ARGS = {
    'intrinsics': intrinsics
}
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 4, 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
patchify Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
princeton-vl/dpvo/dpvo/utils.py
code served (permissive licence) · get_code("7e9ef04c656a01f5")
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 5, dtype family float, shape (2, 108, 4, 3, 3) 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
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects:
# - x: a 5D tensor of shape (b, n, c, h, w) representing video frames
# - patch_size: an integer for the patch extraction size

# Create a small video tensor: (batch=2, frames=3, channels=4, height=8, width=8)
x = torch.randn(2, 3, 4, 8, 8)

# patch_size should be smaller than the spatial dimensions
patch_size = 3

ARGS = {
    "x": x,
    "patch_size": patch_size,
}
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 5, dtype family float, shape (2, 108, 4, 3, 3) — shape (2, 108, 4, 3, 3) 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
iproj Not yet run
unverified (harvested, no recorded run)
princeton-vl/dpvo/dpvo/projective_ops.py
code served (permissive licence) · get_code("81f07dc8d5fcae2c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 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
coords_grid 1 other paper
1 dated earlier
2401.01887 (2024-01)
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry
coords_grid_with_index 1 other paper
1 dated earlier
2401.01887 (2024-01)
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry
extract_intrinsics 1 other paper
1 dated earlier
2401.01887 (2024-01)
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry
iproj 1 other paper
1 dated earlier
2401.01887 (2024-01)
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

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

Recent work in Visual Odometry and SLAM has shown the effectiveness of using deep network backbones. Despite excellent accuracy, such approaches are often expensive to run or do not generalize well zero-shot. To address this problem, we introduce Deep Patch Visual-SLAM, a new system for monocular visual SLAM based on the DPVO visual odometry system. We introduce two loop closure mechanisms which significantly improve the accuracy with minimal runtime and memory overhead. On real-world datasets, DPV-SLAM runs at 1x-3x real-time framerates. We achieve comparable accuracy to DROID-SLAM on Eu-RoC and TartanAir while running twice as fast using a third of the VRAM. We also outperform DROID-SLAM by large margins on KITTI.

For agents

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

get_harvested_code_for_paper("2408.01654")
get_code_for_paper("2408.01654")
have("2408.01654")

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

curl https://syntology.ai/api/ran/2408.01654.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.01654.svg)](https://syntology.ai/paper/2408.01654)

Connect an agent — have() is free.