SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.10556 · 2019

Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference

arXiv · PDF · Open in the Atlas

Code that ran

10 of 18 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; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 2 failures of our instrument; 8 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/1902.10556.json · badge: /api/ran/1902.10556.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
YoYo000/MVSNet canonical (classifier label)
classifier basis: census
10 ran · 8 no recorded run
FunctionStatusWhere it lives
center_image Ran
ran on a synthesized input
YoYo000/MVSNet/mvsnet/preprocess.py
code served (permissive licence) · get_code("fb6a94f3be766ec1")
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 (2, 3, 4) 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

# The function takes an image as input and normalizes it
# by computing mean and variance across spatial dimensions (0, 1)
# The image should be a numpy array with shape (height, width, channels)

# Create a small test image: 2x3 spatial dimensions with 4 channels
np.random.seed(0)
img = np.random.randint(0, 256, size=(2, 3, 4), dtype=np.uint8)

ARGS = {
    "img": img
}
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 ndarray, ndim 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 4) 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
get_pixel_grids Ran
ran on a synthesized input
YoYo000/MVSNet/mvsnet/homography_warping.py
code served (permissive licence) · get_code("65b4ef5776e10fbc")
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 EagerTensor, ndim 1, dtype family float, shape (36,) 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 tensorflow as tf

# The function takes height and width parameters
# height and width should be integers representing image dimensions
# The function creates pixel coordinate grids, so we use small integer values

height = 4
width = 3

ARGS = {
    "height": height,
    "width": width,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float, shape (36,) — shape (36,) 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
layer Ran
ran on a synthesized input
YoYo000/MVSNet/cnn_wrapper/network.py
code served (permissive licence) · get_code("664f1649e11743ea")
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 tensorflow as tf

class MockNetworkLayer:
    """Mock network class that supports the layer decorator pattern."""
    
    def __init__(self):
        self.inputs = None
        self.terminals = []
        self.layers = {}
        self._unique_names = {}
    
    def get_unique_name(self, name):
        """Generate unique layer names."""
        if name not in self._unique_names:
            self._unique_names[name] = 0
        else:
            self._unique_names[name] += 1
        return f"{name}_{self._unique_names[name]}"
    
    def feed(self, layer_output):
        """Update terminals with new layer output."""
        self.terminals = [layer_output]


def mock_op(self, *args, **kwargs):
    """Mock operation that returns a tensor."""
    if len(args) > 0 and isinstance(args[0], tf.Tensor):
        return args[0]
    return tf.constant([[1.0, 2.0], [3.0, 4.0]])


# Create a mock layer decorator function for testing
def layer(op):
    """Decorator for composable network layers."""

    def layer_decorated(self, *args, **kwargs):
        """Layer decoration."""
        if self.inputs is None or (len(args) > 0 and isinstance(args[0], tf.Tensor)):
            layer_output = op(self, *args, **kwargs)
            return layer_output
        name = kwargs.setdefault('name', self.get_unique_name(op.__name__))
        if not self.terminals:
            raise RuntimeError('No input variables found for layer %s.' % name)
        elif len(self.terminals) == 1:
            layer_input = self.terminals[0]
        else:
            layer_input = list(self.terminals)
        layer_output = op(self, layer_input, *args, **kwargs)
        self.layers[name] = layer_output
        self.feed(layer_output)
        return self
    return layer_decorated


# Create test instance
mock_network = MockNetworkLayer()

# Create a decorated operation
@layer
def mock_decorated_op(self, *args, **kwargs):
    """A mock decorated operation."""
    if len(args) > 0 and isinstance(args[0], tf.Tensor):
        return args[0]
    return tf.constant([[1.0, 2.0], [3.0, 4.0]])


ARGS = {
    'op': mock_op
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
less_one_percentage Ran
ran on a synthesized input
YoYo000/MVSNet/mvsnet/loss.py
code served (permissive licence) · get_code("508777ab9599fcfa")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small tensors for the function arguments
batch_size = 2
height = 4
width = 3
channels = 1

# y_true: tensor with some zero and non-zero values
y_true = tf.constant(
    [[[[1.0], [2.0], [0.0]],
      [[3.0], [0.0], [1.5]],
      [[2.5], [1.0], [0.0]],
      [[0.0], [0.5], [1.2]]],
     [[[0.0], [2.0], [1.0]],
      [[1.5], [3.0], [0.0]],
      [[0.0], [0.0], [2.0]],
      [[1.0], [0.5], [0.0]]]],
    dtype=tf.float32
)

# y_pred: predicted values with same shape as y_true
y_pred = tf.constant(
    [[[[1.1], [2.1], [0.0]],
      [[3.2], [0.0], [1.6]],
      [[2.4], [1.1], [0.0]],
      [[0.0], [0.6], [1.3]]],
     [[[0.0], [2.2], [1.1]],
      [[1.6], [3.1], [0.0]],
      [[0.0], [0.0], [2.1]],
      [[1.1], [0.4], [0.0]]]],
    dtype=tf.float32
)

# interval: tensor with scale values for each sample in batch
interval = tf.constant([1.0, 1.0], dtype=tf.float32)

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
    'interval': interval
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
less_three_percentage Ran
ran on a synthesized input
YoYo000/MVSNet/mvsnet/loss.py
code served (permissive licence) · get_code("d41d9b5c9ef21f1d")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Create small test tensors with distinct dimensions
batch_size = 2
height = 4
width = 3
channels = 1

# y_true: batch_size x height x width x channels
# Contains some zeros and some non-zero values
y_true = tf.constant([
    [[[1.0], [2.0], [3.0]],
     [[4.0], [0.0], [5.0]],
     [[6.0], [7.0], [0.0]],
     [[8.0], [9.0], [10.0]]],
    
    [[[0.0], [1.5], [2.5]],
     [[3.5], [4.5], [0.0]],
     [[5.5], [6.5], [7.5]],
     [[0.0], [8.5], [9.5]]]
], dtype=tf.float32)

# y_pred: batch_size x height x width x channels
# Predictions close to true values
y_pred = tf.constant([
    [[[1.1], [2.2], [3.3]],
     [[4.1], [0.1], [5.2]],
     [[6.3], [7.1], [0.2]],
     [[8.2], [9.3], [10.1]]],
    
    [[[0.1], [1.6], [2.6]],
     [[3.6], [4.6], [0.1]],
     [[5.6], [6.6], [7.6]],
     [[0.2], [8.6], [9.6]]]
], dtype=tf.float32)

# interval: scaling factor for each batch element
# Shape: [batch_size]
interval = tf.constant([1.0, 2.0], dtype=tf.float32)

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
    'interval': interval
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
non_zero_mean_absolute_diff Ran
ran on a synthesized input
YoYo000/MVSNet/mvsnet/loss.py
code served (permissive licence) · get_code("d70ba71e56667c49")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small test tensors
batch_size = 2
height = 4
width = 3
channels = 5

# y_true: batch of images with some zero and non-zero values
y_true = tf.constant(
    np.random.randn(batch_size, height, width, channels).astype(np.float32)
)
# Set some values to zero to test masking
y_true_np = y_true.numpy()
y_true_np[0, 0, 0, 0] = 0.0
y_true_np[0, 1, 1, 1] = 0.0
y_true = tf.constant(y_true_np)

# y_pred: predicted images with same shape
y_pred = tf.constant(
    np.random.randn(batch_size, height, width, channels).astype(np.float32)
)

# interval: scaling factors for each batch element
interval = tf.constant([1.5, 2.0], dtype=tf.float32)

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
    'interval': interval,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
random_brightness Ran
ran on a synthesized input
YoYo000/MVSNet/mvsnet/photometric_augmentation.py
code served (permissive licence) · get_code("5516b4b5cdcb1b3f")
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 EagerTensor, ndim 4, dtype family float, shape (2, 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 tensorflow as tf
import numpy as np

# Create a small valid image tensor
# TensorFlow expects images as float32 in range [0, 255] or [0, 1]
# Using shape [batch=2, height=4, width=3, channels=3] for a small RGB image batch
image_data = np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8).astype(np.float32)
image = tf.constant(image_data)

ARGS = {
    "image": image,
    "max_abs_change": 50
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 3) — shape (2, 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_cameras_binary Ran
ran; our contract draft was wrong, not the code
YoYo000/MVSNet/mvsnet/colmap2mvsnet.py
code served (permissive licence) · get_code("0bf4b207ce0d106a")
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) 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 collections
import struct
import numpy as np
import tempfile
import os

CameraModel = collections.namedtuple('CameraModel', ['model_id', 'model_name', 'num_params'])

Camera = collections.namedtuple('Camera', ['id', 'model', 'width', 'height', 'params'])

CAMERA_MODELS = {CameraModel(model_id=0, model_name='SIMPLE_PINHOLE', num_params=3), CameraModel(model_id=1, model_name='PINHOLE', num_params=4), CameraModel(model_id=2, model_name='SIMPLE_RADIAL', num_params=4), CameraModel(model_id=3, model_name='RADIAL', num_params=5), CameraModel(model_id=4, model_name='OPENCV', num_params=8), CameraModel(model_id=5, model_name='OPENCV_FISHEYE', num_params=8), CameraModel(model_id=6, model_name='FULL_OPENCV', num_params=12), CameraModel(model_id=7, model_name='FOV', num_params=5), CameraModel(model_id=8, model_name='SIMPLE_RADIAL_FISHEYE', num_params=4), CameraModel(model_id=9, model_name='RADIAL_FISHEYE', num_params=5), CameraModel(model_id=10, model_name='THIN_PRISM_FISHEYE', num_params=12)}

CAMERA_MODEL_IDS = dict([(camera_model.model_id, camera_model) for camera_model in CAMERA_MODELS])

# Create a temporary binary file with valid camera data
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.bin')
temp_path = temp_file.name

try:
    # Write number of cameras (2 cameras)
    num_cameras = 2
    temp_file.write(struct.pack('<Q', num_cameras))
    
    # Write first camera
    camera_id_1 = 1
    model_id_1 = 1  # PINHOLE with 4 params
    width_1 = 640
    height_1 = 480
    params_1 = [500.0, 500.0, 320.0, 240.0]  # fx, fy, cx, cy
    temp_file.write(struct.pack('<iiQQ', camera_id_1, model_id_1, width_1, height_1))
    temp_file.write(struct.pack('<' + 'd' * 4, *params_1))
    
    # Write second camera
    camera_id_2 = 2
    model_id_2 = 2  # SIMPLE_RADIAL with 4 params
    width_2 = 800
    height_2 = 600
    params_2 = [600.0, 400.0, 300.0, 0.1]  # fx, fy, cx, cy, k1
    temp_file.write(struct.pack('<iiQQ', camera_id_2, model_id_2, width_2, height_2))
    temp_file.write(struct.pack('<' + 'd' * 4, *params_2))
    
    temp_file.close()
    
    ARGS = {
        'path_to_model_file': temp_path
    }
    
finally:
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — 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
read_cameras_text Ran
ran; our contract draft was wrong, not the code
YoYo000/MVSNet/mvsnet/colmap2mvsnet.py
code served (permissive licence) · get_code("8a38e306ff4c5b42")
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) 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 collections
import numpy as np
import tempfile
import os

Camera = collections.namedtuple('Camera', ['id', 'model', 'width', 'height', 'params'])

# Create a temporary file with valid camera data in the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_path = temp_file.name

# Write sample camera data
# Format: camera_id model width height params...
temp_file.write("# Camera list\n")
temp_file.write("1 SIMPLE_PINHOLE 640 480 320.5 240.5 500.0\n")
temp_file.write("2 PINHOLE 800 600 400.0 300.0 600.0 0.1\n")
temp_file.close()

ARGS = {
    'path': temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — 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
read_next_bytes Ran
ran, honoured the contract we drafted
YoYo000/MVSNet/mvsnet/colmap2mvsnet.py
code served (permissive licence) · get_code("56858e04e6fdb2ff")
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) 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 struct
import io

# Create a binary file-like object with test data
# We'll pack some values and then read them back
test_data = struct.pack('<hfi', 42, 3.14, 100)
fid = io.BytesIO(test_data)

ARGS = {
    'fid': fid,
    'num_bytes': 10,  # 2 bytes (h) + 4 bytes (f) + 4 bytes (i) = 10 bytes
    'format_char_sequence': 'hfi',
    'endian_character': '<'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
additive_gaussian_noise Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/photometric_augmentation.py
code served (permissive licence) · get_code("9499c3d39859fe34")
How it ran

no invocation recorded.

additive_speckle_noise Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/photometric_augmentation.py
code served (permissive licence) · get_code("63609fc857bc30cc")
How it ran

no invocation recorded.

get_homographies Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/homography_warping.py
code served (permissive licence) · get_code("860b5f837d298c97")
How it ran

no invocation recorded.

get_homographies_inv_depth Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/homography_warping.py
code served (permissive licence) · get_code("1b40e5386ec51bef")
How it ran

no invocation recorded.

get_propability_map Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/model.py
code served (permissive licence) · get_code("c560e7c5717864e3")
How it ran

no invocation recorded.

group_norm Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/convgru.py
code served (permissive licence) · get_code("d9c4145b6e4c91ff")
How it ran

no invocation recorded.

read_gipuma_dmb Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/depthfusion.py
code served (permissive licence) · get_code("f6147a9b9d73ca5e")
How it ran

no invocation recorded.

scale_camera Not yet run
unverified (harvested, no recorded run)
YoYo000/MVSNet/mvsnet/preprocess.py
code served (permissive licence) · get_code("234f6f5aa22f6f5c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 7 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 7 later) and 11 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
read_next_bytes 70 other papers
1 dated earlier, 69 later
1804.00650 (2018-04)
DeepMVS: Learning Multi-view Stereopsis
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
1912.11744 (2019-12)
Planar Prior Assisted PatchMatch Multi-View Stereo
and 67 more not named here
read_cameras_text 37 other papers
37 later
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
1912.11744 (2019-12)
Planar Prior Assisted PatchMatch Multi-View Stereo
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
and 34 more not named here
read_cameras_binary 21 other papers
21 later
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
1912.11744 (2019-12)
Planar Prior Assisted PatchMatch Multi-View Stereo
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
and 18 more not named here
read_gipuma_dmb 5 other papers
5 later
1905.02706 (2019-05)
Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency
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 2 more not named here
center_image 1 other paper
1 later
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
layer 1 other paper
1 later
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
scale_camera 1 other paper
1 later
2007.10872 (2020-07)
Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

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

Deep learning has recently demonstrated its excellent performance for multi-view stereo (MVS). However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the learned MVS hard to be applied to high-resolution scenes. In this paper, we introduce a scalable multi-view stereo framework based on the recurrent neural network. Instead of regularizing the entire 3D cost volume in one go, the proposed Recurrent Multi-view Stereo Network (R-MVSNet) sequentially regularizes the 2D cost maps along the depth direction via the gated recurrent unit (GRU). This reduces dramatically the memory consumption and makes high-resolution reconstruction feasible. We first show the state-of-the-art performance achieved by the proposed R-MVSNet on the recent MVS benchmarks. Then, we further demonstrate the scalability of the proposed method on several large-scale scenarios, where previous learned approaches often fail due to the memory constraint. Code is available at https://github.com/YoYo000/MVSNet.

For agents

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

get_harvested_code_for_paper("1902.10556")
get_code_for_paper("1902.10556")
have("1902.10556")

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

curl https://syntology.ai/api/ran/1902.10556.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.10556.svg)](https://syntology.ai/paper/1902.10556)

Connect an agent — have() is free.