SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.08430 · 2022

DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments

arXiv · PDF · Open in the Atlas

Code that ran

15 of 16 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 12 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2209.08430.json · badge: /api/ran/2209.08430.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
geniussh/dytanvo canonical (classifier label)
classifier basis not recorded on the link
15 ran · 1 no recorded run
FunctionStatusWhere it lives
ReadMiddleburyFloFile Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/util_flow.py
code served (permissive licence) · get_code("8c56b67cf7c8f5e9")
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 struct
import tempfile
import os

# Create a temporary .FLO file for testing
def create_test_flo_file():
    """Create a minimal valid .FLO file"""
    fd, path = tempfile.mkstemp(suffix='.flo')
    
    width = 2
    height = 3
    
    with os.fdopen(fd, 'wb') as f:
        # Write tag
        f.write(struct.pack('f', 202021.25))
        # Write width
        f.write(struct.pack('i', width))
        # Write height
        f.write(struct.pack('i', height))
        
        # Write flow data (u, v pairs)
        # Create width * height * 2 floats
        flow_data = []
        for i in range(width * height):
            flow_data.append(float(i))  # u value
            flow_data.append(float(i + 0.5))  # v value
        
        for val in flow_data:
            f.write(struct.pack('f', val))
    
    return path

# Create test file
test_flo_path = create_test_flo_file()

ARGS = {
    'path': test_flo_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 — 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
bilinear_interpolate Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/utils.py
code served (permissive licence) · get_code("eac7cea00909cdb1")
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 1, dtype family float, shape (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 math

torch.manual_seed(0)

# The function expects:
# - img: a 3D array/tensor with shape (height, width, channels)
#        accessed via img[h0, w0, :], img[h1, w0, :], etc.
# - h: a float representing a height coordinate
# - w: a float representing a width coordinate

# Create a small 3D image tensor (height=5, width=4, channels=3)
img = torch.randn(5, 4, 3)

# Create float coordinates that are within and between pixel boundaries
h = 2.3  # A float coordinate between pixels
w = 1.7  # A float coordinate between pixels

ARGS = {
    "img": img,
    "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 1, dtype family float, shape (3,) — shape (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
calculate_angle_distance_from_du_dv Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/utils.py
code served (permissive licence) · get_code("2e8164dab6d3aaa3")
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

# The function takes du and dv (which are used in arctan2, sqrt operations)
# and flagDegree (a boolean flag)
# These should be numpy arrays or scalars

du = np.array([1.0, 2.0, 3.0, 4.0])
dv = np.array([0.5, 1.5, 2.5, 3.5])
flagDegree = False

ARGS = {
    'du': du,
    'dv': dv,
    'flagDegree': flagDegree
}
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
conv Ran
ran on a synthesized input
geniussh/dytanvo/Network/VOFlowNet.py
code served (permissive licence) · get_code("7f98f965fb7b7664")
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': 64,
    'kernel_size': 3,
    'stride': 2,
    'padding': 1,
    'dilation': 1,
    'bn_layer': False,
    'bias': 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
cow_masks Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/cowmask.py
code served (permissive licence) · get_code("ebed68087ad2a9d5")
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 2, dtype family float, shape (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 math
import numpy as np
from scipy import special
from scipy.signal import convolve

np.random.seed(0)

ARGS = {
    "mask_size": (4, 3),
    "log_sigma_range": (0.0, 1.0),
    "max_sigma": 2.0,
    "prop_range": (0.3, 0.7),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (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
dataloader Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/segmask_gt.py
code served (permissive licence) · get_code("f5b3005dfa2f221f")
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 2, 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 os
import tempfile
import shutil

# Create a temporary directory structure that mimics the expected file layout
tmpdir = tempfile.mkdtemp()

# Create nested directory structure for level=6 (6 levels deep with optical_flow)
base_path = os.path.join(tmpdir, 'a', 'b', 'c', 'd', 'e', 'f')
os.makedirs(base_path, exist_ok=True)

# Create optical_flow directory and subdirectories
flow_dir = os.path.join(base_path, 'optical_flow', 'into_future', 'left')
os.makedirs(flow_dir, exist_ok=True)

# Create frames_cleanpass directory at same level
frames_dir = os.path.join(base_path, 'frames_cleanpass', 'into_future', 'left')
os.makedirs(frames_dir, exist_ok=True)

# Create disparity and disparity_change directories
disp_dir = os.path.join(base_path, 'disparity', 'into_future', 'left')
os.makedirs(disp_dir, exist_ok=True)

disp_change_dir = os.path.join(base_path, 'disparity_change', 'into_future', 'left')
os.makedirs(disp_change_dir, exist_ok=True)

# Create camera_data directory
camera_dir = os.path.join(base_path, 'camera_data')
os.makedirs(camera_dir, exist_ok=True)

# Create dummy optical flow files
flow_file_0 = os.path.join(flow_dir, 'OpticalFlow_0001_L.pfm')
flow_file_1 = os.path.join(flow_dir, 'OpticalFlow_0002_L.pfm')
open(flow_file_0, 'w').close()
open(flow_file_1, 'w').close()

# Create dummy frame files
frame_file_0 = os.path.join(frames_dir, '0001.png')
frame_file_1 = os.path.join(frames_dir, '0002.png')
open(frame_file_0, 'w').close()
open(frame_file_1, 'w').close()

# Create dummy disparity files
disp_file_0 = os.path.join(disp_dir, '0001.pfm')
open(disp_file_0, 'w').close()

# Create dummy disparity_change files
disp_change_file = os.path.join(disp_change_dir, '0001.pfm')
open(disp_change_file, 'w').close()

# Create camera_data.txt file
camera_file = os.path.join(camera_dir, 'camera_data.txt')
with open(camera_file, 'w') as f:
    f.write('dummy camera data\n')

# Construct the filepath to pass to dataloader
filepath = os.path.join(tmpdir, 'a')

ARGS = {
    'filepath': filepath,
    'fpass': 'frames_cleanpass',
    'level': 6
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, 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
deconv Ran
ran; our contract draft was wrong, not the code
geniussh/dytanvo/Network/PWC/PWCNet.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from yanqi1811/PWC-Net, is pointer only (licence: NOASSERTION) · get_code("dc4fb7628379691e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from yanqi1811/PWC-Net, 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.

default_loader Ran
ran, honoured the contract we drafted
geniussh/dytanvo/Datasets/segmask_gt.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from xlgsyzp/cvpt, is pointer only (licence: NONE) · get_code("ac269a0e4b8d946e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from xlgsyzp/cvpt, 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.

gaussian_kernels Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/cowmask.py
code served (permissive licence) · get_code("39ce5e39be408410")
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 2, dtype family float, shape (1, 39) 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 math
import numpy as np

ARGS = {
    "sigma": 1.5,
    "max_sigma": 3.0,
}
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 2, dtype family float, shape (1, 39) — shape (1, 39) 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
linear Ran
ran on a synthesized input
geniussh/dytanvo/Network/VOFlowNet.py
code served (permissive licence) · get_code("76b6b373246b70ce")
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": 4,
    "out_planes": 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
point_vec Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/flowlib.py
code served (permissive licence) · get_code("57b52bbafbfeb9dc")
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 (992, 1488, 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 numpy as np
import cv2

# Create a small optical flow array
# Shape: (height, width, 2) where last dimension is (u, v) components
height, width = 32, 48
flow = np.random.randn(height, width, 2).astype(np.float32) * 5

# Create a small image array
# Shape: (height, width, 3) for RGB
img = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)

# Add a third channel to flow for the mask/validity indicator
# The function checks flow[j, i, 2] to see if the point is valid
flow_with_mask = np.zeros((height, width, 3), dtype=np.float32)
flow_with_mask[:, :, 0] = flow[:, :, 0]  # u component
flow_with_mask[:, :, 1] = flow[:, :, 1]  # v component
flow_with_mask[:, :, 2] = 1  # validity mask - set to 1 for valid points

ARGS = {
    "img": img,
    "flow": flow_with_mask,
    "skip": 10
}
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 (992, 1488, 3) — shape (992, 1488, 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
predict_flow Ran
ran; our contract draft was wrong, not the code
geniussh/dytanvo/Network/PWC/PWCNet.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from yanqi1811/PWC-Net, is pointer only (licence: NOASSERTION) · get_code("c3f23a008d953af5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from yanqi1811/PWC-Net, 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.

readPFM Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/util_flow.py
code served (permissive licence) · get_code("5b0e5fbaa471b5a6")
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
# PFM format: header (PF or Pf) + dimensions + scale + binary float data

def create_test_pfm_file():
    """Create a temporary PFM file with valid format"""
    temp_file = tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pfm')
    
    # Write header for color image (PF)
    temp_file.write(b'PF\n')
    
    # Write dimensions: width=4, height=3
    temp_file.write(b'4 3\n')
    
    # Write scale (positive for big-endian)
    temp_file.write(b'1.0\n')
    
    # Write binary data: 3 channels * 4 width * 3 height = 36 floats
    data = np.random.randn(3, 4, 3).astype('>f')  # big-endian float
    data.tofile(temp_file)
    
    temp_file.close()
    return temp_file.name

pfm_file_path = create_test_pfm_file()

ARGS = {
    'file': pfm_file_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
tensor2img Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/utils.py
code served (permissive licence) · get_code("88f43b983cf1477b")
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, 5, 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 tensor image with shape (C, H, W) where C=3 (RGB channels)
# The function expects tensImg to be iterable over channels
tensImg = torch.randn(3, 4, 5).float()

# Define mean and std for normalization (one per channel)
mean = [0.5, 0.4, 0.3]
std = [0.2, 0.2, 0.2]

ARGS = {
    "tensImg": tensImg,
    "mean": mean,
    "std": std
}
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 ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
visualize_flow Ran
ran on a synthesized input
geniussh/dytanvo/Datasets/flowlib.py
code served (permissive licence) · get_code("f005258de9141052")
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 numpy as np

# Create a small optical flow array
# Shape: (height, width, 2) where last dimension is [u, v] components
height, width = 4, 3
flow = np.random.randn(height, width, 2).astype(np.float32) * 5.0

ARGS = {
    "flow": flow,
    "mode": "Y"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, 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
cupy_kernel Not yet run
unverified (harvested, no recorded run)
geniussh/dytanvo/Network/PWC/correlation.py
code served (permissive licence) · get_code("679ea21d9a01d383")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 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 (9 with at least one paper dated earlier, 1 the same month, 3 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
default_loader 27 other papers
18 dated earlier, 1 the same month, 8 later
1710.03463 (2017-10)
Learning to Generalize: Meta-Learning for Domain Generalization
1803.08669 (2018-03)
Pyramid Stereo Matching Network
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices
and 24 more not named here
predict_flow 11 other papers
9 dated earlier, 2 later
1709.02371 (2017-09)
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
1807.09190 (2018-07)
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
1810.10510 (2018-10)
Neighbourhood Consensus Networks
and 8 more not named here
deconv 9 other papers
7 dated earlier, 2 later
1709.02371 (2017-09)
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
1807.09190 (2018-07)
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
1810.10510 (2018-10)
Neighbourhood Consensus Networks
and 6 more not named here
bilinear_interpolate 1 other paper
1 dated earlier
2011.00359 (2020-11)
TartanVO: A Generalizable Learning-based VO
calculate_angle_distance_from_du_dv 1 other paper
1 dated earlier
2011.00359 (2020-11)
TartanVO: A Generalizable Learning-based VO
conv 1 other paper
1 dated earlier
2011.00359 (2020-11)
TartanVO: A Generalizable Learning-based VO
cupy_kernel 1 other paper
1 dated earlier
2011.00359 (2020-11)
TartanVO: A Generalizable Learning-based VO
linear 1 other paper
1 dated earlier
2011.00359 (2020-11)
TartanVO: A Generalizable Learning-based VO
tensor2img 1 other paper
1 dated earlier
2011.00359 (2020-11)
TartanVO: A Generalizable Learning-based VO

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

Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments. Semantic segmentation is largely used to discard dynamic associations before estimating camera motions but at the cost of discarding static features and is hard to scale up to unseen categories. In this paper, we leverage the mutual dependence between camera ego-motion and motion segmentation and show that both can be jointly refined in a single learning-based framework. In particular, we present DytanVO, the first supervised learning-based VO method that deals with dynamic environments. It takes two consecutive monocular frames in real-time and predicts camera ego-motion in an iterative fashion. Our method achieves an average improvement of 27.7% in ATE over state-of-the-art VO solutions in real-world dynamic environments, and even performs competitively among dynamic visual SLAM systems which optimize the trajectory on the backend. Experiments on plentiful unseen environments also demonstrate our method's generalizability.

For agents

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

get_harvested_code_for_paper("2209.08430")
get_code_for_paper("2209.08430")
have("2209.08430")

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

curl https://syntology.ai/api/ran/2209.08430.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.08430.svg)](https://syntology.ai/paper/2209.08430)

Connect an agent — have() is free.