SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.10042 · 2020

Non-Local Spatial Propagation Network for Depth Completion

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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 1 has no contract verdict; 1 failure 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/2007.10042.json · badge: /api/ran/2007.10042.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
zzangjinsun/NLSPN_ECCV20 canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
conv_bn_relu Ran
ran; our contract draft was wrong, not the code
zzangjinsun/NLSPN_ECCV20/src/model/common.py
pointer only (licence: MIT); the stored copy get_code serves, from wudiqx106/LFRD2, is pointer only (licence: NONE) · get_code("6cb043ab22719b0a")
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 wudiqx106/LFRD2, 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.

convert_str_to_num Ran
ran, honoured the contract we drafted
zzangjinsun/NLSPN_ECCV20/src/utility.py
code served (permissive licence) · get_code("f8ca3cb40c015a0b")
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 1, dtype family int; 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - val: a string that contains numbers separated by commas, potentially with quotes
# - t: a string indicating the type ('int' or 'float')
# The function removes quotes, splits by comma, and converts to the specified type

ARGS = {
    'val': "'1,2,3'",
    't': 'int'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — 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
make_optimizer_scheduler Ran
ran on a synthesized input
zzangjinsun/NLSPN_ECCV20/src/utility.py
code served (permissive licence) · get_code("ac1d9fa412ad7df0")
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
import torch.optim as optim

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

class Args:
    def __init__(self):
        self.lr = 0.001
        self.weight_decay = 1e-5
        self.optimizer = 'ADAM'
        self.momentum = 0.9
        self.betas = (0.9, 0.999)
        self.epsilon = 1e-8
        self.decay = '10,20,30'
        self.gamma = '1.0,0.1,0.01'

ARGS = {
    'args': Args(),
    'target': SimpleModel()
}
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
get_resnet18 Not yet run
unverified (harvested, no recorded run)
zzangjinsun/NLSPN_ECCV20/src/model/common.py
code served (permissive licence) · get_code("d3f8a892fddc538a")
How it ran

no invocation recorded.

get_resnet34 Not yet run
unverified (harvested, no recorded run)
zzangjinsun/NLSPN_ECCV20/src/model/common.py
code served (permissive licence) · get_code("31c1784010ed8209")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 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
conv_bn_relu 3 other papers
3 later
2303.05021 (2023-03)
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
2405.11867 (2024-05)
Depth Prompting for Sensor-Agnostic Depth Estimation
2511.01704 (2025-11)
Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond
convert_str_to_num 3 other papers
3 later
2303.05021 (2023-03)
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
2404.19294 (2024-04)
Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
2406.11711 (2024-06)
OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
get_resnet18 3 other papers
3 later
2303.05021 (2023-03)
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
2405.11867 (2024-05)
Depth Prompting for Sensor-Agnostic Depth Estimation
2406.11711 (2024-06)
OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
get_resnet34 3 other papers
3 later
2303.05021 (2023-03)
DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
2405.11867 (2024-05)
Depth Prompting for Sensor-Agnostic Depth Estimation
2406.11711 (2024-06)
OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations
make_optimizer_scheduler 1 other paper
1 later
2303.05021 (2023-03)
DiffusionDepth: Diffusion Denoising Approach for Monocular 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

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem. Our implementation is publicly available on the project page.

For agents

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

get_harvested_code_for_paper("2007.10042")
get_code_for_paper("2007.10042")
have("2007.10042")

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

curl https://syntology.ai/api/ran/2007.10042.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.10042.svg)](https://syntology.ai/paper/2007.10042)

Connect an agent — have() is free.