SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.06791 · 2018

Depth-aware CNN for RGB-D Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 5 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/1803.06791.json · badge: /api/ran/1803.06791.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
laughtervv/DepthAwareCNN canonical (classifier label)
classifier basis: census
4 ran · 4 no recorded run
aksh1501/DepthAware_CNN_edit community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
contiguous Ran
ran on a synthesized input
aksh1501/DepthAware_CNN_edit/utils/gradcheck.py
code served (permissive licence) · get_code("aa4b1a72a86182e3")
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 2, dtype family float, shape (2, 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 torch
from torch.autograd import Variable
from collections.abc import Iterable

torch.manual_seed(0)

# Test cases for different input types
tensor_input = torch.randn(2, 4)
variable_input = Variable(torch.randn(3, 5))
list_input = [torch.randn(2, 4), torch.randn(3, 5)]
tuple_input = (torch.randn(2, 4), torch.randn(3, 5))
nested_input = [torch.randn(2, 4), (torch.randn(3, 5), torch.randn(4, 6))]
scalar_input = 42

# Test with a tensor that might not be contiguous
non_contiguous_tensor = torch.randn(2, 4, 5).transpose(0, 1)

ARGS = {
    "input": tensor_input
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
label_accuracy_score Ran
ran on a synthesized input
laughtervv/DepthAwareCNN/utils/util.py
code served (permissive licence) · get_code("c47ae52360c6b10a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small sample data for label_accuracy_score
# The function expects:
# - label_trues: list of 2D arrays with true labels
# - label_preds: list of 2D arrays with predicted labels
# - n_class: number of classes
# - returniu: boolean flag

n_class = 3

# Create two sample images (2D label maps)
# Image 1: 4x5 label map
label_true_1 = np.array([
    [0, 1, 2, 0, 1],
    [1, 2, 0, 1, 2],
    [2, 0, 1, 2, 0],
    [0, 1, 2, 0, 1]
], dtype=np.int32)

label_pred_1 = np.array([
    [0, 1, 2, 0, 1],
    [1, 2, 1, 1, 2],
    [2, 0, 1, 2, 0],
    [0, 1, 2, 1, 1]
], dtype=np.int32)

# Image 2: 3x4 label map (different size to show flexibility)
label_true_2 = np.array([
    [1, 0, 2, 1],
    [2, 1, 0, 2],
    [0, 2, 1, 0]
], dtype=np.int32)

label_pred_2 = np.array([
    [1, 0, 2, 1],
    [2, 1, 1, 2],
    [0, 2, 1, 1]
], dtype=np.int32)

label_trues = [label_true_1, label_true_2]
label_preds = [label_pred_1, label_pred_2]

ARGS = {
    "label_trues": label_trues,
    "label_preds": label_preds,
    "n_class": n_class,
    "returniu": False
}
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, 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
labelcolormap Ran
ran on a synthesized input
laughtervv/DepthAwareCNN/utils/util.py
code served (permissive licence) · get_code("48d8d1e1855aa6dd")
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 int, shape (35, 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

def uint82bin(n, count=8):
    """returns the binary of integer n, count refers to amount of bits"""
    return ''.join([str(n >> y & 1) for y in range(count - 1, -1, -1)])

def labelcolormap(N):
    if N == 35:
        cmap = np.array([(0, 0, 0), (0, 0, 0), (0, 0, 0), (0, 0, 0), (0, 0, 0), (111, 74, 0), (81, 0, 81), (128, 64, 128), (244, 35, 232), (250, 170, 160), (230, 150, 140), (70, 70, 70), (102, 102, 156), (190, 153, 153), (180, 165, 180), (150, 100, 100), (150, 120, 90), (153, 153, 153), (153, 153, 153), (250, 170, 30), (220, 220, 0), (107, 142, 35), (152, 251, 152), (70, 130, 180), (220, 20, 60), (255, 0, 0), (0, 0, 142), (0, 0, 70), (0, 60, 100), (0, 0, 90), (0, 0, 110), (0, 80, 100), (0, 0, 230), (119, 11, 32), (0, 0, 142)], dtype=np.uint8)
    else:
        cmap = np.zeros((N, 3), dtype=np.uint8)
        for i in range(N):
            r, g, b = (0, 0, 0)
            id = i
            for j in range(7):
                str_id = uint82bin(id)
                r = r ^ np.uint8(str_id[-1]) << 7 - j
                g = g ^ np.uint8(str_id[-2]) << 7 - j
                b = b ^ np.uint8(str_id[-3]) << 7 - j
                id = id >> 3
            cmap[i, 0] = r
            cmap[i, 1] = g
            cmap[i, 2] = b
    return cmap

ARGS = {
    "N": 35
}
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 int, shape (35, 3) — shape (35, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_jacobian Ran
ran on a synthesized input
aksh1501/DepthAware_CNN_edit/utils/gradcheck.py
code served (permissive licence) · get_code("8c31f5f90a12d378")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.autograd import Variable
from collections.abc import Iterable

torch.manual_seed(0)

# Test case 1: Variable without requires_grad - should return None
input_no_grad = Variable(torch.randn(2, 4), requires_grad=False)

# Test case 2: Variable with requires_grad - should return jacobian tensor
input_with_grad = Variable(torch.randn(3, 5), requires_grad=True)

# Test case 3: Plain tensor - should return jacobian tensor
input_tensor = torch.randn(2, 4)

# Test case 4: Iterable of tensors - should return filtered jacobians
input_iterable = [
    Variable(torch.randn(2, 3), requires_grad=True),
    torch.randn(4, 2),
    Variable(torch.randn(1, 5), requires_grad=False)
]

# Number of outputs for jacobian
num_out = 6

# Choose one of the test cases for ARGS
ARGS = {
    "input": input_iterable,
    "num_out": num_out
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_layers Ran
ran on a synthesized input
laughtervv/DepthAwareCNN/models/VGG_Deeplab.py
code served (permissive licence) · get_code("b0ad13db5a53e1a2")
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)

# Define a minimal DepthConv class since it's used in make_layers
class DepthConv(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=3, padding=1):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, padding=padding)
    
    def forward(self, x):
        return self.conv(x)

cfg = {'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M']}

depth_cfg = {'D': [0, 3, 6, 10, 14]}

ARGS = {
    'cfg': cfg['D'],
    'depth_cfg': depth_cfg['D'],
    'batch_norm': False,
    'depthconv': False
}
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
uint82bin Ran
ran; our contract draft was wrong, not the code
laughtervv/DepthAwareCNN/utils/util.py
code served (permissive licence) · get_code("098a8251265f82c2")
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 str. 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 numpy as np

# The function uint82bin converts an unsigned integer to its binary representation
# Parameters:
# - n: an integer to convert to binary
# - count: number of bits in the output (default 8)

ARGS = {
    'n': 42,
    'count': 8
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
create_model Not yet run
unverified (harvested, no recorded run)
laughtervv/DepthAwareCNN/models/models.py
code served (permissive licence) · get_code("2550125e25acce91")
How it ran

no invocation recorded.

cross_entropy2d Not yet run
unverified (harvested, no recorded run)
laughtervv/DepthAwareCNN/models/losses.py
code served (permissive licence) · get_code("8a7cda981e891b1b")
How it ran

no invocation recorded.

get_numerical_jacobian Not yet run
unverified (harvested, no recorded run)
aksh1501/DepthAware_CNN_edit/utils/gradcheck.py
code served (permissive licence) · get_code("72271df9d7f8f6ad")
How it ran

no invocation recorded.

vgg16 Not yet run
unverified (harvested, no recorded run)
laughtervv/DepthAwareCNN/models/VGG_Deeplab.py
code served (permissive licence) · get_code("b6bdfbe93eac1645")
How it ran

no invocation recorded.

vgg16_bn Not yet run
unverified (harvested, no recorded run)
laughtervv/DepthAwareCNN/models/VGG_Deeplab.py
code served (permissive licence) · get_code("fa8c10bd6c94939c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 10 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
uint82bin 5 other papers
5 later
1810.04020 (2018-10)
A Comprehensive Survey of Deep Learning for Image Captioning
1902.09777 (2019-02)
Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
2005.08104 (2020-05)
Single-Stage Semantic Segmentation from Image Labels
and 2 more not named here

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

Convolutional neural networks (CNN) are limited by the lack of capability to handle geometric information due to the fixed grid kernel structure. The availability of depth data enables progress in RGB-D semantic segmentation with CNNs. State-of-the-art methods either use depth as additional images or process spatial information in 3D volumes or point clouds. These methods suffer from high computation and memory cost. To address these issues, we present Depth-aware CNN by introducing two intuitive, flexible and effective operations: depth-aware convolution and depth-aware average pooling. By leveraging depth similarity between pixels in the process of information propagation, geometry is seamlessly incorporated into CNN. Without introducing any additional parameters, both operators can be easily integrated into existing CNNs. Extensive experiments and ablation studies on challenging RGB-D semantic segmentation benchmarks validate the effectiveness and flexibility of our approach.

For agents

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

get_harvested_code_for_paper("1803.06791")
get_code_for_paper("1803.06791")
have("1803.06791")

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

curl https://syntology.ai/api/ran/1803.06791.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.06791.svg)](https://syntology.ai/paper/1803.06791)

Connect an agent — have() is free.