SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.16404 · 2020

Unsupervised Monocular Depth Learning in Dynamic Scenes

arXiv · PDF · Open in the Atlas

Code that ran

9 of 14 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 9 have no contract verdict; 0 failures 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/2010.16404.json · badge: /api/ran/2010.16404.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
chamorajg/pytorch_depth_and_motion_planning community (classifier label)
classifier basis not recorded on the link
9 ran · 5 no recorded run
FunctionStatusWhere it lives
create_scales Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/object_motion_net.py
code served (permissive licence) · get_code("faaf4f641fd06913")
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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "constraint_minimum": 0.1
}
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, 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
downsample_conv Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/depth_prediction_net.py
code served (permissive licence) · get_code("34f844c4d6859b89")
How it ran

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

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 16,
    "kernel_size": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
invert_intrinsics_matrix Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/intrinsics_utils.py
code served (permissive licence) · get_code("d310f629b4dc1eab")
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 3, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create a valid intrinsics matrix of shape [2, 3, 3]
# Standard intrinsics matrix format:
# [fx  0  x0]
# [ 0 fy  y0]
# [ 0  0   1]

intrinsics_mat = torch.tensor([
    [[500.0,   0.0, 320.0],
     [  0.0, 500.0, 240.0],
     [  0.0,   0.0,   1.0]],
    [[600.0,   0.0, 400.0],
     [  0.0, 600.0, 300.0],
     [  0.0,   0.0,   1.0]]
], dtype=torch.float32)

ARGS = {
    "intrinsics_mat": intrinsics_mat
}
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 3, dtype family float, shape (2, 3, 3) — shape (2, 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
joint_bilateral_smoothing Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/regularizers.py
code served (permissive licence) · get_code("f3d5d2fef2fa0301")
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

torch.manual_seed(0)

# Create small tensors for smoothed and reference
# smoothed: [B, C1, H, W] where B=2, C1=3, H=4, W=5
smoothed = torch.randn(2, 3, 4, 5)

# reference: [B, C2, H, W] where B=2, C2=4, H=4, W=5
# C2 is different from C1 to show they can be distinct
reference = torch.randn(2, 4, 4, 5)

ARGS = {
    "smoothed": smoothed,
    "reference": reference,
}
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
l1smoothness Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/regularizers.py
code served (permissive licence) · get_code("d51b0d2cba4ec212")
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

torch.manual_seed(0)

# Create a small tensor of shape [B, C, H, W]
# B=2 (batch), C=4 (channels), H=3 (height), W=5 (width)
tensor = torch.randn(2, 4, 3, 5)

ARGS = {
    "tensor": tensor,
    "wrap_around": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
multiply_no_nan Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/consistency_losses.py
code served (permissive licence) · get_code("05aae2be5b1a6d2a")
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

torch.manual_seed(0)

# Create two small tensors for multiplication
# Including NaN values to test the nan-handling behavior
a = torch.tensor([[1.0, 2.0, float('nan'), 4.0],
                   [5.0, float('nan'), 7.0, 8.0]])

b = torch.tensor([[2.0, 3.0, 4.0, float('nan')],
                   [1.0, 2.0, float('nan'), 3.0]])

ARGS = {
    'a': a,
    'b': b
}
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
predict_disp Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/depth_prediction_net.py
code served (permissive licence) · get_code("ac775cd34edc68e6")
How it ran

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

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 64
}
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
predict_disp_softplus Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/depth_prediction_net.py
code served (permissive licence) · get_code("ed06dacb56e6e43d")
How it ran

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

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 64
}
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
torch_gather_nd Ran
ran on a synthesized input
chamorajg/pytorch_depth_and_motion_planning/resampler.py
code served (permissive licence) · get_code("c8b7730e0c7673fd")
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, 128, 416, 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

torch.manual_seed(0)

# params: a tensor that will be reshaped to (batch, 128, 416, -1)
# We need to construct it with appropriate size
# Shape: (2, 128, 416, 4) so it reshapes cleanly
params = torch.randn(2, 128, 416, 4)

# indices: a 2d tensor representing locations [a, b, c, d]
# The function expects indices of shape (batch_size, spatial_dim_1, spatial_dim_2)
# with last dimension containing index values
# Let's create indices with shape (2, 3, 5, 4) for 4D indexing into reshaped params
indices = torch.randint(0, 128, (2, 3, 5, 4), dtype=torch.long)

# Ensure indices are valid for the target dimensions
indices[:, :, :, 0] = torch.randint(0, 2, (2, 3, 5))    # batch dimension
indices[:, :, :, 1] = torch.randint(0, 128, (2, 3, 5))  # first spatial
indices[:, :, :, 2] = torch.randint(0, 416, (2, 3, 5))  # second spatial
indices[:, :, :, 3] = torch.randint(0, 4, (2, 3, 5))    # last dimension

ARGS = {
    "params": params,
    "indices": indices
}
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, 128, 416, 4) — shape (2, 128, 416, 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
normalize_motion_map Not yet run
unverified (harvested, no recorded run)
chamorajg/pytorch_depth_and_motion_planning/regularizers.py
code served (permissive licence) · get_code("55df63b0a869e96a")
How it ran

no invocation recorded.

quadraric_distortion_scale Not yet run
unverified (harvested, no recorded run)
chamorajg/pytorch_depth_and_motion_planning/transform_depth_map.py
code served (permissive licence) · get_code("61088714c224db51")
How it ran

no invocation recorded.

resampler_with_unstacked_warp Not yet run
unverified (harvested, no recorded run)
chamorajg/pytorch_depth_and_motion_planning/resampler.py
code served (permissive licence) · get_code("c672fee27f34d7db")
How it ran

no invocation recorded.

safe_gather_nd Not yet run
unverified (harvested, no recorded run)
chamorajg/pytorch_depth_and_motion_planning/resampler.py
code served (permissive licence) · get_code("66685ae892f9d0f8")
How it ran

no invocation recorded.

unstacked_matrix_from_angles Not yet run
unverified (harvested, no recorded run)
chamorajg/pytorch_depth_and_motion_planning/transform_utils.py
code served (permissive licence) · get_code("01d85bca1ff8df1a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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
downsample_conv 1 other paper
1 dated earlier
1805.09806 (2018-05)
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
predict_disp 1 other paper
1 dated earlier
1805.09806 (2018-05)
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

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

We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy achieved in prior work for dynamic scenes, including methods that require semantic input. Code is at https://github.com/google-research/google-research/tree/master/depth_and_motion_learning .

For agents

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

get_harvested_code_for_paper("2010.16404")
get_code_for_paper("2010.16404")
have("2010.16404")

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

curl https://syntology.ai/api/ran/2010.16404.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.16404.svg)](https://syntology.ai/paper/2010.16404)

Connect an agent — have() is free.