SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.00665 · 2022

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 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/2206.00665.json · badge: /api/ran/2206.00665.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
autonomousvision/monosdf community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_scale_and_shift Ran
ran; our contract draft was wrong, not the code
autonomousvision/monosdf/code/model/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from ethanygao/Aux-NAS, is pointer only (licence: NONE) · get_code("25ba9b5031480973")
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 ethanygao/Aux-NAS, 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.

get_embedder Ran
ran; our contract draft was wrong, not the code
autonomousvision/monosdf/code/model/embedder.py
code served (permissive licence) · get_code("bb0e12df9c0d2a05")
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)

ARGS = {
    'multires': 4,
    'input_dims': 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 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
load_poses Ran
ran, honoured the contract we drafted
autonomousvision/monosdf/scannet_eval/evaluate.py
code served (permissive licence) · get_code("b5dfc40a6055fa6b")
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 1, dtype family float, shape (0,) 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 numpy as np
import os
import tempfile
import shutil

# Create a temporary directory structure that mimics the scannet data layout
temp_dir = tempfile.mkdtemp()
scan_dir = os.path.join(temp_dir, 'data', 'scannet', 'scan123')
pose_dir = os.path.join(scan_dir, 'pose')
os.makedirs(pose_dir, exist_ok=True)

# Create some pose files (every 10th one will be used)
# Create 30 pose files so that with [::10] we get 3 poses
for i in range(30):
    pose_file = os.path.join(pose_dir, f'{i}.txt')
    # Create a 4x4 pose matrix (camera-to-world transformation)
    pose_matrix = np.array([
        [1.0, 0.0, 0.0, 0.1 * i],
        [0.0, 1.0, 0.0, 0.2 * i],
        [0.0, 0.0, 1.0, 0.3 * i],
        [0.0, 0.0, 0.0, 1.0]
    ])
    np.savetxt(pose_file, pose_matrix)

# Monkey-patch the data path lookup to use our temp directory
original_join = os.path.join
def patched_join(*args):
    result = original_join(*args)
    if 'scannet' in result and '../data' in result:
        result = result.replace('../data', os.path.join(temp_dir, 'data'))
    return result

os.path.join = patched_join

try:
    ARGS = {
        'scan_id': '123'
    }
finally:
    # Restore original os.path.join
    os.path.join = original_join
    # Clean up temp directory after ARGS is defined
    shutil.rmtree(temp_dir, ignore_errors=True)
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (0,) — shape (0,) 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
nn_correspondance Ran
ran, violated the contract we drafted
autonomousvision/monosdf/scannet_eval/evaluate.py
pointer only (licence: MIT); the stored copy get_code serves, from zju3dv/nd-sdf, is pointer only (licence: NONE) · get_code("fc70092fdcd3efa2")
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 zju3dv/nd-sdf, 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.

reduction_batch_based Ran
ran; our contract draft was wrong, not the code
autonomousvision/monosdf/code/model/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from ethanygao/Aux-NAS, is pointer only (licence: NONE) · get_code("e8996630fe3501e1")
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 ethanygao/Aux-NAS, 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.

reduction_image_based Not yet run
unverified (harvested, no recorded run)
autonomousvision/monosdf/code/model/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from ethanygao/Aux-NAS, is pointer only (licence: NONE) · get_code("c92f0115a72bf454")
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 ethanygao/Aux-NAS, 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 6 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
get_embedder 22 other papers
3 dated earlier, 19 later · 3 only as an assembly brick
2106.10689 (2021-06)
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
2106.12052 (2021-06)
Volume Rendering of Neural Implicit Surfaces
2205.15848 (2022-05)
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction
and 19 more not named here
reduction_batch_based 5 other papers
1 dated earlier, 4 later
2109.10563 (2021-09)
Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2308.07868 (2023-08)
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces
and 2 more not named here
compute_scale_and_shift 3 other papers
3 later
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2308.07868 (2023-08)
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces
2405.05695 (2024-05)
Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
reduction_image_based 3 other papers
3 later
2306.05720 (2023-06)
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
2308.07868 (2023-08)
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces
2405.05695 (2024-05)
Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
nn_correspondance 2 other papers
2 later
2308.07868 (2023-08)
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces
2408.12598 (2024-08)
ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction
load_poses 1 other paper
1 later
2308.07868 (2023-08)
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces

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 recent years, neural implicit surface reconstruction methods have become popular for multi-view 3D reconstruction. In contrast to traditional multi-view stereo methods, these approaches tend to produce smoother and more complete reconstructions due to the inductive smoothness bias of neural networks. State-of-the-art neural implicit methods allow for high-quality reconstructions of simple scenes from many input views. Yet, their performance drops significantly for larger and more complex scenes and scenes captured from sparse viewpoints. This is caused primarily by the inherent ambiguity in the RGB reconstruction loss that does not provide enough constraints, in particular in less-observed and textureless areas. Motivated by recent advances in the area of monocular geometry prediction, we systematically explore the utility these cues provide for improving neural implicit surface reconstruction. We demonstrate that depth and normal cues, predicted by general-purpose monocular estimators, significantly improve reconstruction quality and optimization time. Further, we analyse and investigate multiple design choices for representing neural implicit surfaces, ranging from monolithic MLP models over single-grid to multi-resolution grid representations. We observe that geometric monocular priors improve performance both for small-scale single-object as well as large-scale multi-object scenes, independent of the choice of representation.

For agents

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

get_harvested_code_for_paper("2206.00665")
get_code_for_paper("2206.00665")
have("2206.00665")

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

curl https://syntology.ai/api/ran/2206.00665.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.00665.svg)](https://syntology.ai/paper/2206.00665)

Connect an agent — have() is free.