SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.00538 · 2019

DPSNet: End-to-end Deep Plane Sweep Stereo

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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 5 have no contract verdict; 3 failures of our instrument; 2 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/1905.00538.json · badge: /api/ran/1905.00538.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
sunghoonim/DPSNet community (classifier label)
classifier basis not recorded on the link
8 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_errors_test Ran
ran on a synthesized input
sunghoonim/DPSNet/loss_functions.py
code served (permissive licence) · get_code("3795ee04b993aecb")
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 1, 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
import numpy as np

torch.manual_seed(0)

# Create small ground truth and prediction tensors
# The function calls .numpy() on both arguments, so they must be torch tensors
gt = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                   [2.0, 3.0, 4.0, 5.0]], dtype=torch.float32)

pred = torch.tensor([[1.1, 2.1, 2.9, 4.2],
                     [2.2, 2.8, 4.1, 4.9]], dtype=torch.float32)

ARGS = {
    "gt": gt,
    "pred": pred
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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
compute_errors_train Ran
ran on a synthesized input
sunghoonim/DPSNet/loss_functions.py
code served (permissive licence) · get_code("56f26f9a1c756e3b")
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 list, ndim 1, 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 small tensors for ground truth, predictions, and validity masks
# gt and pred should have shape (batch_size, spatial_dims...)
# valid should be a boolean mask with the same shape

batch_size = 2
spatial_size = 4

# Ground truth depth maps: shape (2, 4)
gt = torch.rand(batch_size, spatial_size) * 10 + 0.1  # avoid zeros for division

# Predicted depth maps: shape (2, 4)
pred = torch.rand(batch_size, spatial_size) * 10 + 0.1  # avoid zeros for division

# Validity masks: shape (2, 4) with boolean values
valid = torch.randint(0, 2, (batch_size, spatial_size)).bool()

ARGS = {
    "gt": gt,
    "pred": pred,
    "valid": valid,
}
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 list, ndim 1, dtype family float — a list 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
convbn Ran
ran; our contract draft was wrong, not the code
sunghoonim/DPSNet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from 3dcvdeveloper/bgnet, is pointer only (licence: NONE) · get_code("15ab3c76823aef7e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from 3dcvdeveloper/bgnet, and GitHub detected no licence in that repository when it was checked. 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.

convbn_3d Ran
ran; our contract draft was wrong, not the code
sunghoonim/DPSNet/models/submodule.py
pointer only (licence: MIT); the stored copy get_code serves, from mickeykang16/temporaleventstereo, is pointer only (licence: NONE) · get_code("46674adf87c5459d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mickeykang16/temporaleventstereo, and GitHub detected no licence in that repository when it was checked. 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.

convtext Ran
ran; our contract draft was wrong, not the code
sunghoonim/DPSNet/models/PSNet.py
code served (permissive licence) · get_code("12ea6024e74f0a0c")
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)

ARGS = {
    "in_planes": 3,
    "out_planes": 16,
    "kernel_size": 3,
    "stride": 1,
    "dilation": 1,
}
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
inverse_warp Ran
ran on a synthesized input
sunghoonim/DPSNet/inverse_warp.py
code served (permissive licence) · get_code("0f5e002aea945fe0")
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, 3, 4, 5) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Define small tensors with distinct dimensions
batch_size = 2
height = 4
width = 5
channels = 3

# feat: [B, CH, H, W]
feat = torch.randn(batch_size, channels, height, width)

# depth: [B, H, W]
depth = torch.randn(batch_size, height, width).abs() + 0.1

# pose: [B, 3, 4] - this is the 6DoF pose as a 3x4 matrix
pose = torch.randn(batch_size, 3, 4)

# intrinsics: [B, 3, 3]
intrinsics = torch.eye(3).unsqueeze(0).expand(batch_size, -1, -1).clone()
intrinsics[0, 0, 0] = 500.0  # focal length x
intrinsics[0, 1, 1] = 500.0  # focal length y
intrinsics[0, 0, 2] = width / 2
intrinsics[0, 1, 2] = height / 2
intrinsics[1] = intrinsics[0].clone()

# intrinsics_inv: [B, 3, 3]
intrinsics_inv = torch.inverse(intrinsics)

# padding_mode
padding_mode = 'zeros'

ARGS = {
    'feat': feat,
    'depth': depth,
    'pose': pose,
    'intrinsics': intrinsics,
    'intrinsics_inv': intrinsics_inv,
    'padding_mode': padding_mode
}
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, 3, 4, 5) — shape (2, 3, 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
pixel2cam Ran
ran on a synthesized input
sunghoonim/DPSNet/inverse_warp.py
code served (permissive licence) · get_code("7d9d5ed0cad1ad89")
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, 3, 4, 5) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create depth tensor: [B, H, W] with batch=2, height=4, width=5
depth = torch.randn(2, 4, 5)

# Create intrinsics_inv matrix: [B, 3, 3]
# This is the inverse of the camera intrinsics matrix
intrinsics_inv = torch.randn(2, 3, 3)

ARGS = {
    "depth": depth,
    "intrinsics_inv": intrinsics_inv,
}
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, 3, 4, 5) — shape (2, 3, 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
tensor2array Ran
ran on a synthesized input
sunghoonim/DPSNet/utils.py
code served (permissive licence) · get_code("e5ca72bb116ddd00")
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 ndarray, ndim 3, dtype family float, shape (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 numpy as np

torch.manual_seed(0)

# Create a 2D tensor (will trigger the first branch)
tensor_2d = torch.randn(4, 3)

# Create arguments dictionary
ARGS = {
    'tensor': tensor_2d,
    'max_value': 255,
    'colormap': 'rainbow'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (4, 3, 3) — shape (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
cam2pixel Not yet run
unverified (harvested, no recorded run)
sunghoonim/DPSNet/inverse_warp.py
code served (permissive licence) · get_code("397deb932e72aeb7")
How it ran

no invocation recorded.

quat2mat Not yet run
unverified (harvested, no recorded run)
sunghoonim/DPSNet/sequence_folderse.py
code served (permissive licence) · get_code("9f46f38f391e2368")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 6 later) and 3 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
convbn 13 other papers
2 dated earlier, 11 later
1803.08669 (2018-03)
Pyramid Stereo Matching Network
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1911.04460 (2019-11)
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
and 10 more not named here
convbn_3d 9 other papers
2 dated earlier, 7 later
1803.08669 (2018-03)
Pyramid Stereo Matching Network
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
1911.04460 (2019-11)
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
and 6 more not named here
compute_errors_train 2 other papers
2 later
1911.10444 (2019-11)
Normal Assisted Stereo Depth Estimation
1912.09697 (2019-12)
DeepSFM: Structure From Motion Via Deep Bundle Adjustment
convtext 2 other papers
2 later
1911.10444 (2019-11)
Normal Assisted Stereo Depth Estimation
1912.09697 (2019-12)
DeepSFM: Structure From Motion Via Deep Bundle Adjustment
cam2pixel 1 other paper
1 dated earlier
1805.09806 (2018-05)
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
compute_errors_test 1 other paper
1 later
1911.10444 (2019-11)
Normal Assisted Stereo Depth Estimation
pixel2cam 1 other paper
1 later
1912.09697 (2019-12)
DeepSFM: Structure From Motion Via Deep 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

Multiview stereo aims to reconstruct scene depth from images acquired by a camera under arbitrary motion. Recent methods address this problem through deep learning, which can utilize semantic cues to deal with challenges such as textureless and reflective regions. In this paper, we present a convolutional neural network called DPSNet (Deep Plane Sweep Network) whose design is inspired by best practices of traditional geometry-based approaches for dense depth reconstruction. Rather than directly estimating depth and/or optical flow correspondence from image pairs as done in many previous deep learning methods, DPSNet takes a plane sweep approach that involves building a cost volume from deep features using the plane sweep algorithm, regularizing the cost volume via a context-aware cost aggregation, and regressing the dense depth map from the cost volume. The cost volume is constructed using a differentiable warping process that allows for end-to-end training of the network. Through the effective incorporation of conventional multiview stereo concepts within a deep learning framework, DPSNet achieves state-of-the-art reconstruction results on a variety of challenging datasets.

For agents

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

get_harvested_code_for_paper("1905.00538")
get_code_for_paper("1905.00538")
have("1905.00538")

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

curl https://syntology.ai/api/ran/1905.00538.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.00538.svg)](https://syntology.ai/paper/1905.00538)

Connect an agent — have() is free.