SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.07710 · CVPR · 2022

PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos

Huaizu Jiang, Xiaowei Zhou, Yiming Xie, Matheus Gadelha, Fengting Yang, Planar Recon

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 1 has no contract verdict; 6 failures 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/2206.07710.json · badge: /api/ran/2206.07710.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
neu-vi/PlanarRecon canonical (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
neu-vi/PlanarRecon/models/matching.py
code served (permissive licence) · get_code("928f0db3e1d697de")
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 Sequential. 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 MLP takes:
# - channels: list of integers representing channel dimensions for Conv1d layers
# - do_bn: boolean flag for whether to include BatchNorm1d

ARGS = {
    "channels": [3, 16, 32, 8],
    "do_bn": True
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
attention Ran
ran; our contract draft was wrong, not the code
neu-vi/PlanarRecon/models/matching.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from tzvikif/SuperGlue, is pointer only (licence: NOASSERTION) · get_code("70702edb93d9116a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from tzvikif/SuperGlue, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

collate_fn Ran
ran on a synthesized input
neu-vi/PlanarRecon/datasets/collate_fn.py
code served (permissive licence) · get_code("921420df51c0bc69")
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 dict. 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 sample data items with all required keys
def create_sample_item():
    return {
        'imgs': torch.randn(3, 4, 5),  # 3 channels, 4x5 image
        'vol_origin': torch.randn(3),
        'vol_origin_partial': torch.randn(3),
        'world_to_aligned_camera': torch.randn(4, 4),
        'proj_matrices': torch.randn(2, 3, 4),  # 2 cameras, 3x4 projection
        'plane_anchors': [torch.randn(5, 3), torch.randn(6, 3)],
        'residual': torch.randn(4, 5),
        'planes': [torch.randn(3), torch.randn(3)],
        'planes_trans': [torch.randn(4, 4), torch.randn(4, 4)],
        'instance_pointnum': torch.tensor([10, 15]),
        'label_list': [torch.tensor([1, 2, 3]), torch.tensor([4, 5, 6])],
        'mean_xyz': torch.randn(3),
        'scene': 'scene_0',
        'fragment': 'fragment_0',
        'epoch': 5,
        'occ_list': [torch.randn(2, 8), torch.randn(2, 8)],
    }

# Create batch of 2 items
list_data = [create_sample_item(), create_sample_item()]

ARGS = {
    'list_data': list_data
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
log_sinkhorn_iterations Ran
ran; our contract draft was wrong, not the code
neu-vi/PlanarRecon/models/matching.py
code served (permissive licence) · get_code("c717f70478b91095")
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 (2, 4, 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

torch.manual_seed(0)

# Analyze the function signature and body:
# - Z: used with torch operations (logsumexp, unsqueeze), appears to be a tensor
#   Dimensions: logsumexp is called on dim=2 and dim=1, suggesting shape (batch, n, m)
# - log_mu: used with unsqueeze, logsumexp operates on it implicitly via Z+v.unsqueeze(1)
#   Shape should be (batch, n)
# - log_nu: similar to log_mu, shape should be (batch, m)
# - iters: int for loop count

# Create small tensors with distinct dimensions
batch_size = 2
n = 4
m = 3

# Z should be shape (batch, n, m) for the logsumexp operations to work
# logsumexp(Z + v.unsqueeze(1), dim=2) expects Z + (batch, m, 1) -> (batch, n, m)
# logsumexp(Z + u.unsqueeze(2), dim=1) expects Z + (batch, 1, m) -> (batch, n, m)
Z = torch.randn(batch_size, n, m)

# log_mu shape (batch, n) - used with unsqueeze(2) in updates
log_mu = torch.randn(batch_size, n)

# log_nu shape (batch, m) - used with unsqueeze(1) in updates
log_nu = torch.randn(batch_size, m)

# Number of iterations
iters = 3

ARGS = {
    "Z": Z,
    "log_mu": log_mu,
    "log_nu": log_nu,
    "iters": iters,
}
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 (2, 4, 3) — shape (2, 4, 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
make_nograd_func Ran
ran; our contract draft was wrong, not the code
neu-vi/PlanarRecon/utils.py
code served (permissive licence) · get_code("a76fc7fb6958f97c")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple function that uses torch operations
def sample_func(x, y):
    # This function performs some torch operations
    result = x + y
    return result

# Test that the function works with gradients enabled
test_x = torch.randn(2, 4, requires_grad=True)
test_y = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "func": sample_func
}
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 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
make_recursive_func Ran
ran; our contract draft was wrong, not the code
neu-vi/PlanarRecon/utils.py
code served (permissive licence) · get_code("b62bec09ceeaca79")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Define a simple function to be made recursive
def example_func(x):
    """A simple function that doubles its input"""
    if isinstance(x, torch.Tensor):
        return x * 2
    elif isinstance(x, (int, float)):
        return x * 2
    else:
        return x

# The make_recursive_func takes a function as its only parameter
ARGS = {
    "func": example_func
}
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 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
tensor2float Ran
ran; our contract draft was wrong, not the code
neu-vi/PlanarRecon/utils.py
code served (permissive licence) · get_code("25616096f605f638")
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 dict. 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)

# The function tensor2float is decorated with make_recursive_func
# It accepts a single parameter 'vars' which can be:
# - A float (returned as-is)
# - A torch.Tensor (scalar or multi-element, converted to float/list of floats)
# - A list, tuple, or dict (recursively processed)
# - Other types raise NotImplementedError

# Test with a nested structure containing various valid types
scalar_tensor = torch.tensor(3.14)
multi_element_tensor = torch.tensor([1.0, 2.0, 3.0, 4.0])
plain_float = 2.71

ARGS = {
    "vars": {
        "scalar": scalar_tensor,
        "multi": multi_element_tensor,
        "float": plain_float,
        "nested_list": [torch.tensor(1.5), 2.5],
        "nested_tuple": (torch.tensor(5.0), 6.0),
    }
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
make_nograd_func 16 other papers
6 dated earlier, 8 later, 2 same year, order not determinable
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
and 13 more not named here
make_recursive_func 14 other papers
6 dated earlier, 7 later, 1 same year, order not determinable
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
2104.00681 (2021-04)
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
and 11 more not named here
MLP 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
1712.07629 (2017-12)
SuperPoint: Self-Supervised Interest Point Detection and Description
2210.12748 (2022-10)
SC-wLS: Towards Interpretable Feed-forward Camera Re-localization
attention 3 other papers
1 dated earlier, 2 later
1712.07629 (2017-12)
SuperPoint: Self-Supervised Interest Point Detection and Description
2210.12748 (2022-10)
SC-wLS: Towards Interpretable Feed-forward Camera Re-localization
2310.01680 (2023-10)
Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation
log_sinkhorn_iterations 1 other paper
1 later
aaai_27915 (2024 (year only))
ResMatch: Residual Attention Learning for Feature Matching
tensor2float 1 other paper
1 dated earlier
2104.00681 (2021-04)
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video

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

Output: 3D Planes (4.06 s) Ground Truth Textured Planes Figure 1. Comparison of the proposed approach, PlanarRecon, and our baseline. Colored planes mean different instances. We also show the textured mesh for our approach. For the multi-view method NeuralRecon [37] + Seq-RANSAC [14], the Sequential RANSAC is used to extract planes after the geometry reconstruction. Our model produces a much more accurate and coherent 3D plane detection in real-time. Best viewed in color.

For agents

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

get_harvested_code_for_paper("2206.07710")
get_code_for_paper("2206.07710")
have("2206.07710")

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

curl https://syntology.ai/api/ran/2206.07710.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.07710.svg)](https://syntology.ai/paper/2206.07710)

Connect an agent — have() is free.