SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.10264 · 2018

Layer-structured 3D Scene Inference via View Synthesis

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; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 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/1807.10264.json · badge: /api/ran/1807.10264.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
VCL3D/SphericalViewSynthesis community (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
FunctionStatusWhere it lives
create_activation Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/models/modules.py
code served (permissive licence) · get_code("113c21d386502541")
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 ReLU. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'activation': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_conv Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/models/modules.py
code served (permissive licence) · get_code("ebcf860c20b1d695")
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 CoordConv360. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'in_size': 3,
    'out_size': 16,
    'conv_type': 'coord',
    'padding': 1,
    'stride': 1,
    'kernel_size': 3,
    'width': 512
}
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 CoordConv360 — a CoordConv360 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CoordConv360 output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_normalization Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/models/modules.py
code served (permissive licence) · get_code("c2b83b6c248e3ce1")
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 BatchNorm2d. 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
from torch import nn

torch.manual_seed(0)

class Identity(nn.Module):
    def forward(self, x):
        return x

def create_normalization(out_size, norm_type):
    if norm_type == 'batchnorm':
        return nn.BatchNorm2d(out_size)
    elif norm_type == 'groupnorm':
        return nn.GroupNorm(out_size // 4, out_size)
    elif norm_type == 'none':
        return Identity()

ARGS = {
    'out_size': 8,
    'norm_type': 'batchnorm'
}
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 BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d 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
dI_du Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/spherical/derivatives.py
code served (permissive licence) · get_code("7db78eb70134e66a")
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, 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

torch.manual_seed(0)

# The function dI_du takes an image tensor and computes gradients along the u (width) dimension
# It expects a 4D tensor: (batch, channels, height, width)
img = torch.randn(2, 3, 4, 5)  # batch=2, channels=3, height=4, width=5

ARGS = {
    'img': img
}
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, 4, 5) — shape (2, 3, 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
dI_duv Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/spherical/derivatives.py
code served (permissive licence) · get_code("87f1803b687f1230")
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

torch.manual_seed(0)

# Create a small image tensor with shape (batch, channels, height, width)
# batch=2, channels=3, height=4, width=5 to have distinct sizes
img = torch.randn(2, 3, 4, 5)

ARGS = {
    "img": img
}
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
dI_dv Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/spherical/derivatives.py
code served (permissive licence) · get_code("7e83652dec2b5882")
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, 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

torch.manual_seed(0)

# Create a small image tensor
# Shape: (batch=2, channels=3, height=4, width=5)
img = torch.randn(2, 3, 4, 5)

ARGS = {
    "img": img
}
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, 4, 5) — shape (2, 3, 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
parse_arguments Ran
ran on a synthesized input
VCL3D/SphericalViewSynthesis/infer.py
code served (permissive licence) · get_code("8e4d142e91b7b4b5")
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 argparse
import sys

# The function parse_arguments takes a list of command-line arguments
# and returns a tuple of (parsed_args, unknown_args) from argparse

# Construct valid arguments as a list of strings
args = [
    '--input_path', '/path/to/input/panorama.jpg',
    '--weights', '/path/to/weights.pth',
    '-g', '0'
]

ARGS = {
    'args': args
}
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 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
coord_x Not yet run
unverified (harvested, no recorded run)
VCL3D/SphericalViewSynthesis/spherical/cartesian.py
code served (permissive licence) · get_code("7c341b6957c50dc3")
How it ran

no invocation recorded.

coord_y Not yet run
unverified (harvested, no recorded run)
VCL3D/SphericalViewSynthesis/spherical/cartesian.py
code served (permissive licence) · get_code("6e52987d3378be52")
How it ran

no invocation recorded.

coord_z Not yet run
unverified (harvested, no recorded run)
VCL3D/SphericalViewSynthesis/spherical/cartesian.py
code served (permissive licence) · get_code("4d3c2be8cb6e79f8")
How it ran

no invocation recorded.

parse_arguments Not yet run
unverified (harvested, no recorded run)
VCL3D/SphericalViewSynthesis/train_lr.py
code served (permissive licence) · get_code("c319c00d91cee329")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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 an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene that is not directly visible. We overcome the challenge posed by the lack of direct supervision by instead leveraging a more naturally available multi-view supervisory signal. Our insight is to use view synthesis as a proxy task: we enforce that our representation (inferred from a single image), when rendered from a novel perspective, matches the true observed image. We present a learning framework that operationalizes this insight using a new, differentiable novel view renderer. We provide qualitative and quantitative validation of our approach in two different settings, and demonstrate that we can learn to capture the hidden aspects of a scene.

For agents

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

get_harvested_code_for_paper("1807.10264")
get_code_for_paper("1807.10264")
have("1807.10264")

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

curl https://syntology.ai/api/ran/1807.10264.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.10264.svg)](https://syntology.ai/paper/1807.10264)

Connect an agent — have() is free.