SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.09283 · 2022

PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 5 have no contract verdict; 0 failures of our instrument; 2 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/2203.09283.json · badge: /api/ran/2203.09283.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
zhijieshen-bjtu/panoformer canonical (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_depth_metrics Ran
ran on a synthesized input
zhijieshen-bjtu/panoformer/PanoFormer/metrics.py
code served (permissive licence) · get_code("8ee1769c0dd17017")
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

torch.manual_seed(0)

# Create small tensor arguments for depth metrics computation
# The function expects gt and pred to be depth tensors
# It performs element-wise operations and reductions

gt = torch.randn(2, 4) + 5.0  # Ground truth depth, shifted to positive range
pred = torch.randn(2, 4) + 5.0  # Predicted depth, shifted to positive range

# Ensure values are in a reasonable range (not too close to 0.1 or 16 boundaries initially)
gt = torch.clamp(gt, 0.5, 15.0)
pred = torch.clamp(pred, 0.5, 15.0)

# Create a mask (optional parameter)
mask = torch.ones(2, 4, dtype=torch.bool)

ARGS = {
    "gt": gt,
    "pred": pred,
    "mask": mask,
    "median_align": 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 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
generate_ref_points Ran
ran on a synthesized input
zhijieshen-bjtu/panoformer/PanoFormer/network/PSA.py
code served (permissive licence) · get_code("23b9363b00ceea5b")
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 (3, 4, 2) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

ARGS = {
    "width": 4,
    "height": 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 Tensor, ndim 3, dtype family float, shape (3, 4, 2) — shape (3, 4, 2) 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_k_layer_feature_map Ran
ran on a synthesized input
zhijieshen-bjtu/panoformer/PanoFormer/network/PSA.py
code served (permissive licence) · get_code("9e82bf4646d4e34c")
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, 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
import torch.nn as nn

torch.manual_seed(0)

# Build a simple sequential model with a few layers
model_layer = nn.Sequential(
    nn.Linear(4, 3),
    nn.ReLU(),
    nn.Linear(3, 5),
    nn.ReLU(),
    nn.Linear(5, 2)
)

# Create a small input tensor (batch_size=2, input_dim=4)
x = torch.randn(2, 4)

# Select a layer index to extract features from
k = 1

ARGS = {
    "model_layer": model_layer,
    "k": k,
    "x": x
}
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, 3) — shape (2, 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
read_list Ran
ran on a synthesized input
zhijieshen-bjtu/panoformer/PanoFormer/matterport3d.py
code served (permissive licence) · get_code("e94322673236e329")
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 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 tempfile
import os

# Create a temporary file with sample data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("image1.jpg depth1.png\n")
temp_file.write("image2.jpg depth2.png\n")
temp_file.write("image3.jpg depth3.png\n")
temp_file.close()

list_file_path = temp_file.name

ARGS = {
    'list_file': list_file_path
}
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 2, 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
restore_scale Ran
ran on a synthesized input
zhijieshen-bjtu/panoformer/PanoFormer/network/PSA.py
code served (permissive licence) · get_code("94e4147279fb4f23")
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)

# The function takes width, height, and ref_point
# ref_point is a tensor that gets cloned and detached, then indexed with [..., 0] and [..., 1]
# This suggests it's a tensor with shape (..., 2) where the last dimension has at least 2 elements

width = 640
height = 480

# Create a ref_point tensor with shape (2, 4) - batch of 2, with 4 values per point
# The last dimension should have at least 2 elements (for indexing [0] and [1])
ref_point = torch.tensor([
    [0.5, 0.3, 0.1, 0.9],
    [0.2, 0.8, 0.4, 0.6]
], dtype=torch.float32)

ARGS = {
    "width": width,
    "height": height,
    "ref_point": ref_point,
}
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
extract_image Not yet run
unverified (harvested, no recorded run)
zhijieshen-bjtu/panoformer/PanoFormer/common.py
code served (permissive licence) · get_code("ed47b6d3840587fc")
How it ran

no invocation recorded.

extract_path Not yet run
unverified (harvested, no recorded run)
zhijieshen-bjtu/panoformer/PanoFormer/common.py
code served (permissive licence) · get_code("6a2f685cb7ea6a39")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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
read_list 1 other paper
1 dated earlier
2202.02796 (2022-02)
GLPanoDepth: Global-to-Local Panoramic Depth Estimation

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

Existing panoramic depth estimation methods based on convolutional neural networks (CNNs) focus on removing panoramic distortions, failing to perceive panoramic structures efficiently due to the fixed receptive field in CNNs. This paper proposes the panorama transformer (named PanoFormer) to estimate the depth in panorama images, with tangent patches from spherical domain, learnable token flows, and panorama specific metrics. In particular, we divide patches on the spherical tangent domain into tokens to reduce the negative effect of panoramic distortions. Since the geometric structures are essential for depth estimation, a self-attention module is redesigned with an additional learnable token flow. In addition, considering the characteristic of the spherical domain, we present two panorama-specific metrics to comprehensively evaluate the panoramic depth estimation models' performance. Extensive experiments demonstrate that our approach significantly outperforms the state-of-the-art (SOTA) methods. Furthermore, the proposed method can be effectively extended to solve semantic panorama segmentation, a similar pixel2pixel task. Code will be available.

For agents

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

get_harvested_code_for_paper("2203.09283")
get_code_for_paper("2203.09283")
have("2203.09283")

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

curl https://syntology.ai/api/ran/2203.09283.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.09283.svg)](https://syntology.ai/paper/2203.09283)

Connect an agent — have() is free.