SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper · CVPR · 2023

GeoMVSNet: Learning Multi-View Stereo with Geometry Perception

Ronggang Wang, Rui Peng, Zhe Zhang, Yuxi Hu

Open in the Atlas

Code that ran

14 of 17 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 6 have no contract verdict; 8 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper.json · badge: /api/ran/Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper.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
doubleZ0108/GeoMVSNet canonical (classifier label)
classifier basis: census
14 ran · 3 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran on a synthesized input
doubleZ0108/GeoMVSNet/models/geometry.py
code served (permissive licence) · get_code("b489862be0d5e045")
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 Conv2d. 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': 64,
    'stride': 1,
    'groups': 1,
    'dilation': 1,
    'bias': False,
    'padding': 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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
convbnrelu Ran
ran on a synthesized input
doubleZ0108/GeoMVSNet/models/geometry.py
code served (permissive licence) · get_code("1ef4059f083c613e")
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_channels": 3,
    "out_channels": 64,
    "kernel_size": 3,
    "stride": 1,
    "padding": 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
deconvbnrelu Ran
ran on a synthesized input
doubleZ0108/GeoMVSNet/models/geometry.py
code served (permissive licence) · get_code("e3ad939a2f4ff10e")
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_channels": 3,
    "out_channels": 64,
    "kernel_size": 5,
    "stride": 2,
    "padding": 2,
    "output_padding": 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
depth_distribution_similarity_loss Ran
ran on a synthesized input
doubleZ0108/GeoMVSNet/models/loss.py
code served (permissive licence) · get_code("5b0386a5403da5e4")
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 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 torch

torch.manual_seed(0)

# Create small tensors for batch size 2
batch_size = 2
height = 4
width = 3

# depth: predicted depth map, shape (batch, height, width)
depth = torch.rand(batch_size, height, width) * 10.0 + 1.0

# depth_gt: ground truth depth map, same shape
depth_gt = torch.rand(batch_size, height, width) * 10.0 + 1.0

# mask: boolean mask, same shape
mask = torch.rand(batch_size, height, width) > 0.3

# depth_min: minimum depth per batch, shape (batch,)
depth_min = torch.tensor([0.5, 0.7])

# depth_max: maximum depth per batch, shape (batch,)
depth_max = torch.tensor([15.0, 18.0])

ARGS = {
    "depth": depth,
    "depth_gt": depth_gt,
    "mask": mask,
    "depth_min": depth_min,
    "depth_max": depth_max,
}
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 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
frequency_domain_filter Ran
ran on a synthesized input
doubleZ0108/GeoMVSNet/models/filter.py
code served (permissive licence) · get_code("6681a1701babd0e1")
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)

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

# Create rho_ratio parameter - controls how much information is filtered
rho_ratio = 2.0

ARGS = {
    "depth": depth,
    "rho_ratio": rho_ratio,
}
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
generate_points_from_depth Ran
ran on a synthesized input
doubleZ0108/GeoMVSNet/fusions/dtu/_open3d.py
code served (permissive licence) · get_code("d2371f03f5c5b250")
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, 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)

# depth: (B, 1, H, W)
# B=2 (batch), H=4 (height), W=3 (width)
depth = torch.randn(2, 1, 4, 3)

# proj: (B, 4, 4) - projection matrix
# Create valid projection matrices (invertible)
proj = torch.zeros(2, 4, 4)
proj[:, 0, 0] = 1.0
proj[:, 1, 1] = 1.0
proj[:, 2, 2] = 1.0
proj[:, 3, 3] = 1.0
proj = proj + 0.01 * torch.randn(2, 4, 4)  # Add small noise to ensure invertibility

ARGS = {
    "depth": depth,
    "proj": proj,
}
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, 3) — shape (2, 3, 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
homo_warping Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
doubleZ0108/GeoMVSNet/models/submodules.py
code served (permissive licence) · get_code("2433e10d0340ac47")
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, 4, 3, 8, 6) 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 as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Define parameters for homo_warping function
B = 2  # batch size
C = 4  # number of channels
Hs, Ws = 8, 6  # source feature height and width
Hr, Wr = 8, 6  # reference height and width
num_depth = 3  # number of depth values

# Create source feature tensor (B, C, Hs, Ws) - 4D case
src_fea = torch.randn(B, C, Hs, Ws)

# Create source projection matrix (B, 4, 4)
src_proj = torch.randn(B, 4, 4)
# Make it invertible by ensuring it's well-conditioned
src_proj = src_proj + torch.eye(4).unsqueeze(0) * 2

# Create reference projection matrix (B, 4, 4)
ref_proj = torch.randn(B, 4, 4)
# Make it invertible by ensuring it's well-conditioned
ref_proj = ref_proj + torch.eye(4).unsqueeze(0) * 2

# Create depth values tensor (B, num_depth, Hr, Wr)
depth_values = torch.rand(B, num_depth, Hr, Wr) * 5 + 0.1  # depth values between 0.1 and 5.1

ARGS = {
    'src_fea': src_fea,
    'src_proj': src_proj,
    'ref_proj': ref_proj,
    'depth_values': depth_values
}
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, 4, 3, 8, 6) — shape (2, 4, 3, 8, 6) 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
init_inverse_range Ran
ran; our contract draft was wrong, not the code
doubleZ0108/GeoMVSNet/models/submodules.py
code served (permissive licence) · get_code("9dc0b1027a30eb55")
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, 3, 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)

# Create small tensors with distinct sizes for different dimensions
batch_size = 2
num_depth_samples = 4
height = 3
width = 5

# cur_depth: shape (batch_size, num_depth_samples)
# This tensor holds depth values at different sample points
cur_depth = torch.tensor([
    [0.5, 1.0, 1.5, 2.0],
    [0.6, 1.2, 1.8, 2.4]
], dtype=torch.float32)

# Number of depth hypothesis points to generate
ndepths = 4

# Device and dtype
device = torch.device('cpu')
dtype = torch.float32

# Height and Width
H = 3
W = 5

ARGS = {
    'cur_depth': cur_depth,
    'ndepths': ndepths,
    'device': device,
    'dtype': dtype,
    'H': H,
    'W': W
}
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, 3, 5) — shape (2, 4, 3, 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
make_nograd_func Ran
ran; our contract draft was wrong, not the code
doubleZ0108/GeoMVSNet/models/utils/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
doubleZ0108/GeoMVSNet/models/utils/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
motion_blur Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
doubleZ0108/GeoMVSNet/datasets/blendedmvs.py
code served (permissive licence) · get_code("4e30ac617a07841b")
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 int, 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 cv2
import numpy as np

# Create a small test image
# The function uses cv2.filter2D which expects a 2D or 3D numpy array
# Let's create a small color image (height=4, width=3, channels=3)
test_img = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

ARGS = {
    'img': test_img,
    'max_kernel_size': 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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 int, 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
read_pfm Ran
ran; our contract draft was wrong, not the code
doubleZ0108/GeoMVSNet/fusions/dtu/_open3d.py
code served (permissive licence) · get_code("6b687b02c05fe850")
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 numpy as np
import tempfile
import os

# Create a temporary PFM file for testing
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.pfm")

# Create a simple PFM file (color, 3-channel)
height, width = 2, 3
data = np.random.rand(height, width, 3).astype(np.float32)

# Write PFM file
with open(temp_file, 'wb') as f:
    # Header: PF for color
    f.write(b'PF\n')
    # Dimensions
    f.write(f'{width} {height}\n'.encode('utf-8'))
    # Scale (negative indicates little-endian)
    f.write(b'-1.0\n')
    # Data (flip vertically to match PFM format, write in little-endian)
    flipped_data = np.flipud(data)
    flipped_data.astype('<f').tofile(f)

ARGS = {
    'filename': temp_file
}
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 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
read_pfm Ran
ran; our contract draft was wrong, not the code
doubleZ0108/GeoMVSNet/datasets/data_io.py
code served (permissive licence) · get_code("b150f19350fbcd98")
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 sys
import re
import numpy as np
import tempfile
import os

# Create a temporary PFM file for testing
def create_test_pfm(filename, width=4, height=3, is_color=True, scale_value=1.0):
    """Create a minimal valid PFM file for testing."""
    with open(filename, 'wb') as f:
        # Write header
        if is_color:
            f.write(b'PF\n')
            num_channels = 3
        else:
            f.write(b'Pf\n')
            num_channels = 1
        
        # Write dimensions
        f.write(f'{width} {height} \n'.encode('utf-8'))
        
        # Write scale (negative indicates little-endian)
        f.write(f'{-scale_value}\n'.encode('utf-8'))
        
        # Write data
        if is_color:
            data = np.random.rand(height, width, 3).astype('<f')
        else:
            data = np.random.rand(height, width).astype('<f')
        
        data = np.flipud(data)
        data.tofile(f)

# Create temporary test file
temp_dir = tempfile.gettempdir()
test_pfm_path = os.path.join(temp_dir, 'test_image.pfm')
create_test_pfm(test_pfm_path, width=4, height=3, is_color=True, scale_value=1.0)

ARGS = {
    'filename': test_pfm_path
}
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 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
schedule_inverse_range Ran
ran; our contract draft was wrong, not the code
doubleZ0108/GeoMVSNet/models/submodules.py
code served (permissive licence) · get_code("afbfac7ff243b94d")
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, 8, 6) 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 function usage:
# - inverse_min_depth: tensor with .device and .dtype attributes, used in indexing [:, None, :, :]
# - inverse_max_depth: tensor with .device and .dtype attributes, used in indexing [:, None, :, :]
# - ndepths: int, used in arange and reshape
# - H: int, used in repeat and interpolate
# - W: int, used in repeat and interpolate

batch_size = 2
height = 8
width = 6
num_depths = 4
spatial_h = height // 2  # 4
spatial_w = width // 2   # 3

# Create inverse_min_depth and inverse_max_depth tensors
# They need shape (batch, H//2, W//2) based on how they're used in the function
inverse_min_depth = torch.ones(batch_size, spatial_h, spatial_w, dtype=torch.float32)
inverse_max_depth = torch.ones(batch_size, spatial_h, spatial_w, dtype=torch.float32) * 0.5

ARGS = {
    "inverse_min_depth": inverse_min_depth,
    "inverse_max_depth": inverse_max_depth,
    "ndepths": num_depths,
    "H": height,
    "W": width,
}
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, 8, 6) — shape (2, 4, 8, 6) 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
geomvsnet_loss Not yet run
unverified (harvested, no recorded run)
doubleZ0108/GeoMVSNet/models/loss.py
code served (permissive licence) · get_code("006f8748226b7ffd")
How it ran

no invocation recorded.

pixel_wise_loss Not yet run
unverified (harvested, no recorded run)
doubleZ0108/GeoMVSNet/models/loss.py
code served (permissive licence) · get_code("796b0dd0cad3182e")
How it ran

no invocation recorded.

tensor2float Not yet run
unverified (harvested, no recorded run)
doubleZ0108/GeoMVSNet/models/utils/utils.py
code served (permissive licence) · get_code("8e28f96374f1b285")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 6 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
make_nograd_func 16 other papers
10 dated earlier, 3 later, 3 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
9 dated earlier, 2 later, 3 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
read_pfm 12 other papers
6 dated earlier, 4 later, 2 same year, order not determinable
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2008.02268 (2020-08)
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
2108.03824 (2021-08)
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
and 9 more not named here
tensor2float 10 other papers
5 dated earlier, 2 later, 3 same year, order not determinable
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
2108.03824 (2021-08)
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
2112.05126 (2021-12)
IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo
and 7 more not named here
homo_warping 2 other papers
1 later, 1 same year, order not determinable
2309.17218 (2023-09)
When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
2507.11333 (2025-07)
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
init_inverse_range 2 other papers
1 dated earlier, 1 same year, order not determinable
2204.07346 (2022-04)
MVSTER: Epipolar Transformer for Efficient Multi-View Stereo
2309.17218 (2023-09)
When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
motion_blur 2 other papers
1 dated earlier, 1 later
2201.01501 (2022-01)
Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
2507.11333 (2025-07)
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
convbnrelu 1 other paper
1 dated earlier
2209.13106 (2022-09)
Simultaneous Acquisition of High Quality RGB Image and Polarization Information using a Sparse Polarization Sensor
schedule_inverse_range 1 other paper
1 dated earlier
2204.07346 (2022-04)
MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

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 cascade Multi-View Stereo (MVS) methods can efficiently estimate high-resolution depth maps through narrowing hypothesis ranges. However, previous methods ignored the vital geometric information embedded in coarse stages, leading to vulnerable cost matching and sub-optimal reconstruction results. In this paper, we propose a geometry awareness model, termed GeoMVSNet, to explicitly integrate geometric clues implied in coarse stages for delicate depth estimation. In particular, we design a twobranch geometry fusion network to extract geometric priors from coarse estimations to enhance structural feature extraction at finer stages. Besides, we embed the coarse probability volumes, which encode valuable depth distribution attributes, into the lightweight regularization network to further strengthen depth-wise geometry intuition. Meanwhile, we apply the frequency domain filtering to mitigate the negative impact of the high-frequency regions and adopt the curriculum learning strategy to progressively boost the geometry integration of the model. To intensify the full-scene geometry perception of our model, we present the depth distribution similarity loss based on the Gaussian-Mixture Model assumption. Extensive experiments on DTU and Tanks and Temples (T&T) datasets demonstrate that our GeoMVSNet achieves state-of-the-art results and ranks first on the T&T-Advanced set. Code is available at https://github.com/doubleZ0108/GeoMVSNet.

For agents

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

get_harvested_code_for_paper("Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper")
get_code_for_paper("Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper")
have("Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper")

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

curl https://syntology.ai/api/ran/Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper.json

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

[![Syntology run record](https://syntology.ai/api/ran/Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper.svg)](https://syntology.ai/paper/Zhang_GeoMVSNet_Learning_Multi-View_Stereo_With_Geometry_Perception_CVPR_2023_paper)

Connect an agent — have() is free.