SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.08149 · 2023

URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 4 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2302.08149.json · badge: /api/ran/2302.08149.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
shuweishao/urcdc-depth canonical (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
FunctionStatusWhere it lives
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shuweishao/urcdc-depth/urcdc/networks/newcrf_layers.py
code served (permissive licence) · get_code("144d10b49baeb8a6")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:38:58Z). If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# Using distinct sizes: 2, 8, 8, 4
x = torch.randn(2, 8, 8, 4)

# window_size must divide both H and W evenly
# H=8, W=8, so window_size=4 works (8 // 4 = 2)
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) — shape (8, 4, 4, 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_num_lines Ran
ran, honoured the contract we drafted
shuweishao/urcdc-depth/urcdc/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from northeastsquare/bts, is pointer only (licence: GPL-3.0) · get_code("050c56fb7282eb88")
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 northeastsquare/bts, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

normalize_result Ran
ran; our contract draft was wrong, not the code
shuweishao/urcdc-depth/urcdc/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from adonis-galaxy/wordepth, is pointer only (licence: NONE) · get_code("8a05ea4d5e917bf4")
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 adonis-galaxy/wordepth, 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.

preprocessing_transforms Ran
ran; our contract draft was wrong, not the code
shuweishao/urcdc-depth/urcdc/dataloaders/dataloader.py
code served (permissive licence) · get_code("4f7c1c530e5b46be")
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 Compose. 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
from PIL import Image
from torchvision import transforms

torch.manual_seed(0)

ARGS = {
    'mode': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
preprocessing_transforms Ran
ran; our contract draft was wrong, not the code
shuweishao/urcdc-depth/urcdc/dataloaders/dataloader_kittipred.py
code served (permissive licence) · get_code("ea623328271af85a")
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 Compose. 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
from PIL import Image

torch.manual_seed(0)

ARGS = {
    'mode': 'train'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
upsample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shuweishao/urcdc-depth/urcdc/networks/NewCRFDepth.py
code served (permissive licence) · get_code("35e6bae6a3fe0669")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 8, 10) 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.functional as F

torch.manual_seed(0)

# Create a small input tensor for upsampling
# Shape: (batch=2, channels=3, height=4, width=5)
x = torch.randn(2, 3, 4, 5)

ARGS = {
    'x': x,
    'scale_factor': 2,
    'mode': 'bilinear',
    'align_corners': 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 Tensor, ndim 4, dtype family float, shape (2, 3, 8, 10) — shape (2, 3, 8, 10) 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
window_reverse Ran
ran; our contract draft was wrong, not the code
shuweishao/urcdc-depth/urcdc/networks/newcrf_layers.py
code served (permissive licence) · get_code("61bf152e6a42a184")
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 Tensor, ndim 4, dtype family float, shape (2, 8, 12, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Parameters for window_reverse
# windows: (num_windows*B, window_size, window_size, C)
# The function expects windows to be partitioned from an image of size (B, H, W, C)
# where the image is divided into non-overlapping windows of size window_size x window_size

B = 2  # batch size
H = 8  # image height
W = 12  # image width
window_size = 4  # window size
C = 3  # number of channels

# Calculate number of windows
num_windows_h = H // window_size  # 2
num_windows_w = W // window_size  # 3
num_windows = num_windows_h * num_windows_w  # 6

# windows shape: (num_windows*B, window_size, window_size, C)
# = (6*2, 4, 4, 3) = (12, 4, 4, 3)
windows = torch.randn(num_windows * B, window_size, window_size, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 8, 12, 3) — shape (2, 8, 12, 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
colorize Not yet run
unverified (harvested, no recorded run)
shuweishao/urcdc-depth/urcdc/utils.py
code served (permissive licence) · get_code("9999af2cf9c1b6bb")
How it ran

no invocation recorded.

is_module_wrapper Not yet run
unverified (harvested, no recorded run)
shuweishao/urcdc-depth/urcdc/networks/newcrf_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Adonis-galaxy/WorDepth, is pointer only (licence: NONE) · get_code("9b9dd29ad0d626a0")
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 Adonis-galaxy/WorDepth, 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. No invocation recorded.

load_url_dist Not yet run
unverified (harvested, no recorded run)
shuweishao/urcdc-depth/urcdc/networks/newcrf_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from w2kun/DCDepth, is pointer only (licence: NONE) · get_code("92dad73ee855852f")
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 w2kun/DCDepth, 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. No invocation recorded.

resize Not yet run
unverified (harvested, no recorded run)
shuweishao/urcdc-depth/urcdc/networks/newcrf_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from w2kun/DCDepth, is pointer only (licence: NONE) · get_code("9012d3fdd4cbaea1")
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 w2kun/DCDepth, 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. 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 10 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 4 the same month, 10 later) and 0 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
window_reverse 227 other papers
75 dated earlier, 4 the same month, 139 later, 9 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
70 dated earlier, 3 the same month, 141 later, 9 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
resize 9 other papers
3 dated earlier, 6 later
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2208.03792 (2022-08)
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
and 6 more not named here
preprocessing_transforms 8 other papers
3 dated earlier, 5 later
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2208.10762 (2022-08)
Depth Map Decomposition for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
and 5 more not named here
get_num_lines 7 other papers
3 dated earlier, 4 later
1907.10326 (2019-07)
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
and 4 more not named here
is_module_wrapper 7 other papers
2 dated earlier, 1 the same month, 4 later · 1 only as an assembly brick
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
2302.06556 (2023-02)
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
and 4 more not named here
load_url_dist 7 other papers
2 dated earlier, 1 the same month, 4 later · 1 only as an assembly brick
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
2302.06556 (2023-02)
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
and 4 more not named here
colorize 5 other papers
2 dated earlier, 3 later
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
2309.14137 (2023-09)
IEBins: Iterative Elastic Bins for Monocular Depth Estimation
and 2 more not named here
normalize_result 5 other papers
2 dated earlier, 3 later
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
2309.14137 (2023-09)
IEBins: Iterative Elastic Bins for Monocular Depth Estimation
and 2 more not named here
upsample 4 other papers
2 dated earlier, 2 later
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
2309.14137 (2023-09)
IEBins: Iterative Elastic Bins for Monocular Depth Estimation
and 1 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

This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and the local information is critical for accurate depth estimation. Towards this end, we introduce an uncertainty rectified cross-distillation between Transformer and convolutional neural network (CNN) to learn a unified depth estimator. Specifically, we use the depth estimates from the Transformer branch and the CNN branch as pseudo labels to teach each other. Meanwhile, we model the pixel-wise depth uncertainty to rectify the loss weights of noisy pseudo labels. To avoid the large capacity gap induced by the strong Transformer branch deteriorating the cross-distillation, we transfer the feature maps from Transformer to CNN and design coupling units to assist the weak CNN branch to leverage the transferred features. Furthermore, we propose a surprisingly simple yet highly effective data augmentation technique CutFlip, which enforces the model to exploit more valuable clues apart from the vertical image position for depth inference. Extensive experiments demonstrate that our model, termed~\textbf{URCDC-Depth}, exceeds previous state-of-the-art methods on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets, even with no additional computational burden at inference time. The source code is publicly available at \url{https://github.com/ShuweiShao/URCDC-Depth}.

For agents

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

get_harvested_code_for_paper("2302.08149")
get_code_for_paper("2302.08149")
have("2302.08149")

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

curl https://syntology.ai/api/ran/2302.08149.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.08149.svg)](https://syntology.ai/paper/2302.08149)

Connect an agent — have() is free.