SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.03706 · 2019

Exploiting temporal consistency for real-time video depth estimation

arXiv · PDF · Open in the Atlas

Code that ran

15 of 20 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 8 have no contract verdict; 6 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/1908.03706.json · badge: /api/ran/1908.03706.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
weihaox/ST-CLSTM community (classifier label)
classifier basis not recorded on the link
15 ran · 5 no recorded run
FunctionStatusWhere it lives
adjust_gt Ran
ran on a synthesized input
weihaox/ST-CLSTM/models/loss.py
code served (permissive licence) · get_code("582daeea4db3c567")
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. 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.functional as F

torch.manual_seed(0)

# gt_depth: a tensor that will be interpolated to match sizes of pred_depth elements
# It needs to be a 4D tensor (batch, channels, height, width)
gt_depth = torch.randn(2, 1, 8, 8)

# pred_depth: a list of tensors, each with size() method that returns a tensor
# with attributes [2] and [3] representing height and width
# Create tensors of different sizes to show interpolation
pred_depth = [
    torch.randn(2, 1, 4, 5),
    torch.randn(2, 1, 6, 7),
]

ARGS = {
    "gt_depth": gt_depth,
    "pred_depth": pred_depth,
}
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 — a list 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
atoi Ran
ran, honoured the contract we drafted
weihaox/ST-CLSTM/create_list_nyuv2.py
pointer only (licence: MIT); the stored copy get_code serves, from harshmaru7/DilatedConv, is pointer only (licence: NONE) · get_code("6dbf1b2a5b901370")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from harshmaru7/DilatedConv, 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.

cal_temporal_loss Ran
ran on a synthesized input
weihaox/ST-CLSTM/models/loss.py
code served (permissive licence) · get_code("234ba1b7c155afdb")
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
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for pred_cls and gt_cls
# pred_cls: logits from model (batch_size=2, num_classes=4)
pred_cls = torch.randn(2, 4)

# gt_cls: ground truth labels (batch_size=2, num_classes=4) with values in [0, 1]
gt_cls = torch.randint(0, 2, (2, 4)).float()

ARGS = {
    "pred_cls": pred_cls,
    "gt_cls": gt_cls,
}
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
colored_depthmap Ran
ran on a synthesized input
weihaox/ST-CLSTM/utils.py
code served (permissive licence) · get_code("ba5b77ab3b38dfa1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (4, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import matplotlib.pyplot as plt

# Create a small depth map (4x3 to have distinct dimensions)
depth = np.random.rand(4, 3) * 10.0

# Define ARGS dict with all parameters
ARGS = {
    "depth": depth,
    "d_min": None,
    "d_max": None,
}
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 float, shape (4, 3, 3) — shape (4, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
weihaox/ST-CLSTM/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, 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.

cubes_2_maps Ran
ran on a synthesized input
weihaox/ST-CLSTM/models/net.py
code served (permissive licence) · get_code("245b6327a43dab16")
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 torch

torch.manual_seed(0)

# The function expects a 5D tensor with shape (b, c, d, h, w)
# It permutes to (b, d, c, h, w), then views to (b*d, c, h, w)
# We'll use distinct sizes: batch=2, channels=3, depth=4, height=5, width=6

cubes = torch.randn(2, 3, 4, 5, 6)

ARGS = {
    "cubes": cubes
}
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 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
densenet121 Ran
ran; our contract draft was wrong, not the code
weihaox/ST-CLSTM/models/densenet.py
code served (permissive licence) · get_code("a32d5ced0147ff13")
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 DenseNet. 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 = {
    'pretrained': 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 DenseNet — a DenseNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseNet 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
densenet169 Ran
ran; our contract draft was wrong, not the code
weihaox/ST-CLSTM/models/densenet.py
code served (permissive licence) · get_code("ce8509f3822ca900")
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 DenseNet. 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 = {
    'pretrained': 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 DenseNet — a DenseNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseNet 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
densenet201 Ran
ran; our contract draft was wrong, not the code
weihaox/ST-CLSTM/models/densenet.py
code served (permissive licence) · get_code("fb44f7825bd55074")
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 DenseNet. 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 = {
    'pretrained': 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 DenseNet — a DenseNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DenseNet 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
maps_2_cubes Ran
ran on a synthesized input
weihaox/ST-CLSTM/models/R_CLSTM_modules.py
code served (permissive licence) · get_code("72d1e8662e40ee5c")
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, 3, 1, 4, 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
import torch.nn as nn

torch.manual_seed(0)

# Construct valid arguments for maps_2_cubes
# The function expects:
# x: a tensor of shape (x_b, x_c, x_h, x_w)
# b: batch size parameter for reshaping
# d: depth parameter for reshaping

# Create a small tensor with distinct dimensions
# x_b=2, x_c=3, x_h=4, x_w=5
x = torch.randn(2, 3, 4, 5)

# b should be a divisor that when multiplied by d gives x_b
# Let's say b=2, d=1, so b*d = 2 = x_b
b = 2
d = 1

ARGS = {
    "x": x,
    "b": b,
    "d": d
}
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, 3, 1, 4, 5) — shape (2, 3, 1, 4, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge_into_row Ran
ran on a synthesized input
weihaox/ST-CLSTM/utils.py
code served (permissive licence) · get_code("6a97398822c13711")
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 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create tiny tensors for the function parameters
# input: expects (C, H, W) shape after transpose, so create (3, 4, 5)
input_tensor = torch.randn(3, 4, 5)

# depth_target: expects (1, H, W) or (H, W) after squeeze
depth_target = torch.randn(1, 4, 5)

# depth_pred: expects (1, H, W) or (H, W) after squeeze, has .data attribute
depth_pred = torch.randn(1, 4, 5)

ARGS = {
    "input": input_tensor,
    "depth_target": depth_target,
    "depth_pred": depth_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, 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
natural_keys Ran
ran; our contract draft was wrong, not the code
weihaox/ST-CLSTM/create_list_nyuv2.py
code served (permissive licence) · get_code("7052cf0436949e37")
How it ran

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

import re

def atoi(text):
    return int(text) if text.isdigit() else text

def natural_keys(text):
    """
    alist.sort(key=natural_keys) sorts in human order
    http://nedbatchelder.com/blog/200712/human_sorting.html
    (See Toothy's implementation in the comments)
    """
    return [atoi(c) for c in re.split('(\\d+)', text)]

# The function takes a single parameter: text (a string)
# It uses string methods: isdigit(), re.split()
# It returns a list of mixed ints and strings

ARGS = {
    "text": "file123name456.txt"
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
resnet18 Ran
ran on a synthesized input
weihaox/ST-CLSTM/models/resnet.py
code served (permissive licence) · get_code("c6a23f12099175fb")
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 ResNet. 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)

# The resnet18 function accepts:
# - pretrained (bool): whether to load pretrained weights
# - **kwargs: additional arguments passed to ResNet constructor (e.g., num_classes)

ARGS = {
    'pretrained': False,  # Set to False to avoid network calls to download pretrained weights
    'num_classes': 1000   # Standard ImageNet number of classes
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran; our contract draft was wrong, not the code
weihaox/ST-CLSTM/models/resnet.py
code served (permissive licence) · get_code("7baa747d63fe9173")
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 ResNet. 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
import math

torch.manual_seed(0)

ARGS = {
    'pretrained': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
video_split Ran
ran on a synthesized input
weihaox/ST-CLSTM/create_list_nyuv2.py
code served (permissive licence) · get_code("c20acf86f01ededc")
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 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyze the function:
# - frame_len: used in range(interval), frame_len - frame_train * interval + 1, frame_len - frame_train * interval - start, frame_len - start
#   These are all integer arithmetic operations, so frame_len should be an int
# - frame_train: used in frame_train * interval, frame_train * interval (appears multiple times)
#   Should be an int
# - interval: used in range(interval), frame_train * interval, sample_interval calculations
#   Should be an int
# - overlap: used in frame_train - overlap
#   Should be an int

# The function constructs indices for video frame splitting
# Let's use reasonable values for a video splitting scenario
# frame_len: total number of frames in video
# frame_train: number of frames to use for training window
# interval: stride/interval between selected frames
# overlap: overlap between consecutive windows

ARGS = {
    "frame_len": 100,
    "frame_train": 10,
    "interval": 2,
    "overlap": 2
}
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 2, dtype family int — 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
cal_spatial_loss Not yet run
unverified (harvested, no recorded run)
weihaox/ST-CLSTM/models/loss.py
code served (permissive licence) · get_code("d54e9906b330185e")
How it ran

no invocation recorded.

maps_2_maps Not yet run
unverified (harvested, no recorded run)
weihaox/ST-CLSTM/models/R_CLSTM_modules.py
code served (permissive licence) · get_code("f1c871b0e9cfd116")
How it ran

no invocation recorded.

se_resnet101 Not yet run
unverified (harvested, no recorded run)
weihaox/ST-CLSTM/models/senet.py
code served (permissive licence) · get_code("004633155d2807e0")
How it ran

no invocation recorded.

se_resnet50 Not yet run
unverified (harvested, no recorded run)
weihaox/ST-CLSTM/models/senet.py
code served (permissive licence) · get_code("7b455b8f464f2797")
How it ran

no invocation recorded.

senet154 Not yet run
unverified (harvested, no recorded run)
weihaox/ST-CLSTM/models/senet.py
code served (permissive licence) · get_code("e4808bbea4a75417")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 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, 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
conv3x3 686 other papers
143 dated earlier, 10 the same month, 533 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet34 53 other papers
17 dated earlier, 36 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 50 more not named here
atoi 13 other papers
1 dated earlier, 12 later
1511.07122 (2015-11)
Multi-Scale Context Aggregation by Dilated Convolutions
2104.08773 (2021-04)
Cross-Task Generalization via Natural Language Crowdsourcing Instructions
2203.03339 (2022-03)
L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments
and 10 more not named here
natural_keys 12 other papers
1 dated earlier, 11 later
1511.07122 (2015-11)
Multi-Scale Context Aggregation by Dilated Convolutions
2203.03339 (2022-03)
L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments
2208.13645 (2022-08)
Finding Near-Optimal Weight Independent Sets at Scale
and 9 more not named here
densenet121 6 other papers
3 dated earlier, 3 later
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
and 3 more not named here
densenet169 6 other papers
3 dated earlier, 3 later
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
and 3 more not named here
densenet201 6 other papers
3 dated earlier, 3 later
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1812.00332 (2018-12)
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
1904.03441 (2019-04)
Iterative Normalization: Beyond Standardization towards Efficient Whitening
and 3 more not named here
colored_depthmap 1 other paper
1 dated earlier
1903.03273 (2019-03)
FastDepth: Fast Monocular Depth Estimation on Embedded Systems
senet154 1 other paper
1 dated earlier
1709.01507 (2017-09)
Squeeze-and-Excitation Networks

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Accuracy of depth estimation from static images has been significantly improved recently, by exploiting hierarchical features from deep convolutional neural networks (CNNs). Compared with static images, vast information exists among video frames and can be exploited to improve the depth estimation performance. In this work, we focus on exploring temporal information from monocular videos for depth estimation. Specifically, we take the advantage of convolutional long short-term memory (CLSTM) and propose a novel spatial-temporal CSLTM (ST-CLSTM) structure. Our ST-CLSTM structure can capture not only the spatial features but also the temporal correlations/consistency among consecutive video frames with negligible increase in computational cost. Additionally, in order to maintain the temporal consistency among the estimated depth frames, we apply the generative adversarial learning scheme and design a temporal consistency loss. The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion. By taking advantage of the temporal information, we build a video depth estimation framework that runs in real-time and generates visually pleasant results. Moreover, our approach is flexible and can be generalized to most existing depth estimation frameworks. Code is available at: https://tinyurl.com/STCLSTM

For agents

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

get_harvested_code_for_paper("1908.03706")
get_code_for_paper("1908.03706")
have("1908.03706")

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

curl https://syntology.ai/api/ran/1908.03706.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.03706.svg)](https://syntology.ai/paper/1908.03706)

Connect an agent — have() is free.