SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.12288 · 2023

ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

arXiv · PDF · Open in the Atlas

Code that ran

12 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 2 have no contract verdict; 9 failures of our instrument; 4 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/2302.12288.json · badge: /api/ran/2302.12288.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
thygate/stable-diffusion-webui-depthmap-script canonical (classifier label)
classifier basis not recorded on the link
10 ran · 4 no recorded run
isl-org/ZoeDepth canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/lib/Resnext_torch.py
code served (permissive licence) · get_code("d9def42110729a85")
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 Conv2d. 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 function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/lib/Resnext_torch.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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 Conv2d. 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,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/lib/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.

estimatezoedepth Ran
ran on a synthesized input
thygate/stable-diffusion-webui-depthmap-script/src/depthmap_generation.py
code served (permissive licence) · get_code("13416aca1c543254")
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 (384, 384) 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
from PIL import Image
import numpy as np

torch.manual_seed(0)

class MockResizer:
    def __init__(self):
        self._Resize__width = 384
        self._Resize__height = 384

class MockPrep(nn.Module):
    def __init__(self):
        super().__init__()
        self.resizer = MockResizer()

class MockCore(nn.Module):
    def __init__(self):
        super().__init__()
        self.prep = MockPrep()

class MockZoeDepthModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.core = MockCore()
    
    def infer_pil(self, img):
        return np.random.rand(384, 384).astype(np.float32)

# Create a small PIL Image
img_array = np.random.randint(0, 256, (256, 256, 3), dtype=np.uint8)
img = Image.fromarray(img_array)

# Create mock model
model = MockZoeDepthModel()

# Width and height parameters
w = 512
h = 480

ARGS = {
    "img": img,
    "model": model,
    "w": w,
    "h": h
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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 2, dtype family float, shape (384, 384) — shape (384, 384) 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_installed_version Ran
ran on a synthesized input
thygate/stable-diffusion-webui-depthmap-script/install.py
code served (permissive licence) · get_code("a467686f61537560")
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 importlib.metadata

# The function get_installed_version takes a package name string and attempts
# to retrieve its installed version using importlib.metadata.version()
# It needs a valid package name as argument.

ARGS = {
    "package": "torch"
}
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 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
infer Ran
ran; our contract draft was wrong, not the code
isl-org/ZoeDepth/evaluate.py
code served (permissive licence) · get_code("8ffddb7d6410c4f1")
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, 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)

class SimpleDepthModel(nn.Module):
    """Minimal depth estimation model that outputs a tensor"""
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(3, 1, kernel_size=3, padding=1)
    
    def forward(self, images, **kwargs):
        # Output a simple tensor of depth values
        return self.conv(images)

# Create model instance
model = SimpleDepthModel()
model.eval()

# Create tiny batch of images: batch_size=2, channels=3, height=4, width=5
images = torch.randn(2, 3, 4, 5)

ARGS = {
    'model': model,
    'images': images,
}
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, 1, 4, 5) — shape (2, 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
load_ckpt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from LiheYoung/Depth-Anything
pointer only · get_code("6ff08048a8305588")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

resnet18 Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/lib/Resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lijia7/sddr, is pointer only (licence: NONE) · get_code("42823db097a59e8e")
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 lijia7/sddr, 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.

resnet34 Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/lib/Resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lijia7/sddr, is pointer only (licence: NONE) · get_code("39037cdb0fe985b1")
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 lijia7/sddr, 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.

scale_torch Ran
ran, honoured the contract we drafted
thygate/stable-diffusion-webui-depthmap-script/src/depthmap_generation.py
pointer only (licence: MIT); the stored copy get_code serves, from compphoto/SIDepth, is pointer only (licence: NOASSERTION) · get_code("9f120435a865e388")
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 compphoto/SIDepth, 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.

strip_prefix_if_present Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/lib/net_tools.py
pointer only (licence: MIT); the stored copy get_code serves, from BIT-DA/SDCA, is pointer only (licence: NONE) · get_code("5a951495ac113177")
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 BIT-DA/SDCA, 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.

weights_init Ran
ran; our contract draft was wrong, not the code
thygate/stable-diffusion-webui-depthmap-script/inpaint/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from IsHYuhi/ST-CGAN_Stacked_Conditional_Generative_Adversarial_Networks, is pointer only (licence: NONE) · get_code("96c6be3581e1f391")
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 IsHYuhi/ST-CGAN_Stacked_Conditional_Generative_Adversarial_Networks, 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.

estimateleres Not yet run
unverified (harvested, no recorded run)
thygate/stable-diffusion-webui-depthmap-script/src/depthmap_generation.py
code served (permissive licence) · get_code("0314372534c03432")
How it ran

no invocation recorded.

get_func Not yet run
unverified (harvested, no recorded run)
thygate/stable-diffusion-webui-depthmap-script/lib/net_tools.py
pointer only (licence: MIT); the stored copy get_code serves, from ForMyCat/SparseGS, is pointer only (licence: NOASSERTION) · get_code("0d504dc72cd88b69")
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 ForMyCat/SparseGS, 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. No invocation recorded.

resnext101_32x8d Not yet run
unverified (harvested, no recorded run)
thygate/stable-diffusion-webui-depthmap-script/lib/Resnext_torch.py
pointer only (licence: MIT); the stored copy get_code serves, from ForMyCat/SparseGS, is pointer only (licence: NOASSERTION) · get_code("ff6eae1654f1ef39")
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 ForMyCat/SparseGS, 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. No invocation recorded.

spectral_norm Not yet run
unverified (harvested, no recorded run)
thygate/stable-diffusion-webui-depthmap-script/inpaint/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from tsingqguo/misf, is pointer only (licence: NONE) · get_code("b189ed0149b76880")
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 tsingqguo/misf, 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 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, 13 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 3 the same month, 13 later) and 3 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
457 dated earlier, 1 the same month, 221 later, 7 same year, order not determinable · 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
conv1x1 431 other papers
240 dated earlier, 5 the same month, 177 later, 8 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
155 dated earlier, 3 the same month, 146 later, 7 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
spectral_norm 14 other papers
11 dated earlier, 2 later, 1 same year, order not determinable · 5 only as an assembly brick
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
1908.00463 (2019-08)
DIODE: A Dense Indoor and Outdoor DEpth Dataset
1911.10375 (2019-11)
Region Normalization for Image Inpainting
and 11 more not named here
strip_prefix_if_present 14 other papers
9 dated earlier, 5 later
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
2104.02323 (2021-04)
Objects are Different: Flexible Monocular 3D Object Detection
2105.05013 (2021-05)
Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
and 11 more not named here
weights_init 8 other papers
5 dated earlier, 2 later, 1 same year, order not determinable
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1712.02478 (2017-12)
Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
and 5 more not named here
resnet18 3 other papers
1 dated earlier, 2 later
2208.13241 (2022-08)
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
2312.00206 (2023-12)
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
2409.17880 (2024-09)
Self-Distilled Depth Refinement with Noisy Poisson Fusion
resnet34 3 other papers
1 dated earlier, 2 later
2208.13241 (2022-08)
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
2312.00206 (2023-12)
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
2409.17880 (2024-09)
Self-Distilled Depth Refinement with Noisy Poisson Fusion
get_func 2 other papers
1 dated earlier, 1 later
2208.13241 (2022-08)
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
2312.00206 (2023-12)
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
resnext101_32x8d 2 other papers
1 dated earlier, 1 later
2208.13241 (2022-08)
Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image
2312.00206 (2023-12)
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
infer 1 other paper
1 later
2401.10891 (2024-01)
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
load_ckpt 1 other paper
1 later
2401.10891 (2024-01)
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
scale_torch 1 other paper
1 later
2406.09374 (2024-06)
Scale-Invariant Monocular Depth Estimation via SSI Depth

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 paper tackles the problem of depth estimation from a single image. Existing work either focuses on generalization performance disregarding metric scale, i.e. relative depth estimation, or state-of-the-art results on specific datasets, i.e. metric depth estimation. We propose the first approach that combines both worlds, leading to a model with excellent generalization performance while maintaining metric scale. Our flagship model, ZoeD-M12-NK, is pre-trained on 12 datasets using relative depth and fine-tuned on two datasets using metric depth. We use a lightweight head with a novel bin adjustment design called metric bins module for each domain. During inference, each input image is automatically routed to the appropriate head using a latent classifier. Our framework admits multiple configurations depending on the datasets used for relative depth pre-training and metric fine-tuning. Without pre-training, we can already significantly improve the state of the art (SOTA) on the NYU Depth v2 indoor dataset. Pre-training on twelve datasets and fine-tuning on the NYU Depth v2 indoor dataset, we can further improve SOTA for a total of 21% in terms of relative absolute error (REL). Finally, ZoeD-M12-NK is the first model that can jointly train on multiple datasets (NYU Depth v2 and KITTI) without a significant drop in performance and achieve unprecedented zero-shot generalization performance to eight unseen datasets from both indoor and outdoor domains. The code and pre-trained models are publicly available at https://github.com/isl-org/ZoeDepth .

For agents

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

get_harvested_code_for_paper("2302.12288")
get_code_for_paper("2302.12288")
have("2302.12288")

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

curl https://syntology.ai/api/ran/2302.12288.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.12288.svg)](https://syntology.ai/paper/2302.12288)

Connect an agent — have() is free.