SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.10689 · 2021

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

14 of 16 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; 3 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 7 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/2106.10689.json · badge: /api/ran/2106.10689.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
Totoro97/NeuS canonical (classifier label)
classifier basis: plan_row
6 ran · 2 no recorded run
sanowar-raihan/meta-neus community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
ventusff/neurecon reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
ishanchadha01/lightneus reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
build_shapenet Ran
ran on a synthesized input
sanowar-raihan/meta-neus/datasets/shapenet.py
code served (permissive licence) · get_code("d76caca25c942469")
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 ShapenetDataset. 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 json
import tempfile
import imageio
from pathlib import Path
import numpy as np

torch.manual_seed(0)

# Create temporary directory structure with mock data
temp_dir = tempfile.TemporaryDirectory()
dataset_root = temp_dir.name

# Create mock object folders with necessary files
num_objects = 2
num_views = 3
img_height, img_width = 64, 80

for obj_idx in range(num_objects):
    obj_folder = Path(dataset_root) / f"object_{obj_idx:06d}"
    obj_folder.mkdir(parents=True, exist_ok=True)
    
    # Create mock transforms.json
    frames = []
    for view_idx in range(num_views):
        # Create a mock image with RGBA channels
        mock_image = np.random.randint(0, 256, (img_height, img_width, 4), dtype=np.uint8)
        image_path = obj_folder / f"view_{view_idx}.png"
        imageio.imwrite(str(image_path), mock_image)
        
        # Create mock transform matrix (4x4)
        transform_matrix = np.eye(4).tolist()
        transform_matrix[0][3] = view_idx * 0.1
        
        frames.append({
            "file_path": f"view_{view_idx}.png",
            "transform_matrix": transform_matrix
        })
    
    transforms_data = {
        "camera_angle_x": 0.7854,  # ~45 degrees
        "frames": frames
    }
    
    transforms_path = obj_folder / "transforms.json"
    with open(transforms_path, 'w') as f:
        json.dump(transforms_data, f)

# Create splits.json
splits_path = Path(dataset_root) / "splits.json"
splits_data = {
    "train": ["object_000000", "object_000001"],
    "val": [],
    "test": []
}
with open(splits_path, 'w') as f:
    json.dump(splits_data, f)

ARGS = {
    "image_set": "train",
    "dataset_root": dataset_root,
    "splits_path": str(splits_path),
    "num_views": num_views
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
imageio, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ShapenetDataset — a ShapenetDataset 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
cdf_Phi_s Ran
ran, honoured the contract we drafted
ventusff/neurecon/models/frameworks/neus.py
code served (permissive licence) · get_code("967d31403271a227")
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)

# x: a tensor that will be multiplied by s and passed to sigmoid
x = torch.randn(2, 4)

# s: a scaling factor (can be a scalar tensor or float)
s = 2.0

ARGS = {
    "x": x,
    "s": s,
}
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
create_posemat Ran
ran on a synthesized input
sanowar-raihan/meta-neus/vis/object_rendering.py
code served (permissive licence) · get_code("1dca0b455d2dd9a8")
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 (4, 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 three scalar parameters: radius, theta, and phi
# These are used in mathematical operations (torch.cos, torch.sin, etc.)
# So they should be float values or 0-d tensors

radius = 5.0
theta = torch.tensor(0.785398)  # approximately pi/4
phi = torch.tensor(1.570796)    # approximately pi/2

ARGS = {
    "radius": radius,
    "theta": theta,
    "phi": phi
}
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 (4, 4) — shape (4, 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_fields Ran
ran; our contract draft was wrong, not the code
Totoro97/NeuS/models/renderer.py
pointer only (licence: MIT); the stored copy get_code serves, from fraunhoferhhi/d-neus, is pointer only (licence: NOASSERTION) · get_code("1f2fc3e977362a4d")
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 fraunhoferhhi/d-neus, and GitHub could not classify the licence of that repository (NOASSERTION). 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_360_poses Ran
ran on a synthesized input
sanowar-raihan/meta-neus/vis/object_rendering.py
code served (permissive licence) · get_code("b547a755ccf17ef4")
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 (120, 4, 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
import math

torch.manual_seed(0)

ARGS = {
    "radius": 2,
    "phi": -math.pi / 5,
    "num_poses": 120,
}
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 (120, 4, 4) — shape (120, 4, 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
get_embedder Ran
ran; our contract draft was wrong, not the code
Totoro97/NeuS/models/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_K_Rt_from_P Ran
ran, honoured the contract we drafted
Totoro97/NeuS/models/dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from 728388808/alpha-NeuS, is pointer only (licence: NONE) · get_code("69986a1a9ebdac78")
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 728388808/alpha-NeuS, 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.

read_cameras_binary Ran
ran; our contract draft was wrong, not the code
Totoro97/NeuS/preprocess_custom_data/colmap_preprocess/colmap_read_model.py
pointer only (licence: MIT); the stored copy get_code serves, from Advanced-Vision-and-Learning-Lab/sparse-view-3dgs-pack, is pointer only (licence: NONE) · get_code("3d7e294ff8567d46")
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 Advanced-Vision-and-Learning-Lab/sparse-view-3dgs-pack, 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.

read_cameras_text Ran
ran; our contract draft was wrong, not the code
Totoro97/NeuS/preprocess_custom_data/colmap_preprocess/colmap_read_model.py
code served (permissive licence) · get_code("8a38e306ff4c5b42")
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) and returned dict. 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 collections
import numpy as np
import tempfile
import os

Camera = collections.namedtuple('Camera', ['id', 'model', 'width', 'height', 'params'])

# Create a temporary file with valid camera data in the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_path = temp_file.name

# Write sample camera data
# Format: camera_id model width height params...
temp_file.write("# Camera list\n")
temp_file.write("1 SIMPLE_PINHOLE 640 480 320.5 240.5 500.0\n")
temp_file.write("2 PINHOLE 800 600 400.0 300.0 600.0 0.1\n")
temp_file.close()

ARGS = {
    'path': temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
read_next_bytes Ran
ran, honoured the contract we drafted
Totoro97/NeuS/preprocess_custom_data/colmap_preprocess/colmap_read_model.py
code served (permissive licence) · get_code("56858e04e6fdb2ff")
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) 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 struct
import io

# Create a binary file-like object with test data
# We'll pack some values and then read them back
test_data = struct.pack('<hfi', 42, 3.14, 100)
fid = io.BytesIO(test_data)

ARGS = {
    'fid': fid,
    'num_bytes': 10,  # 2 bytes (h) + 4 bytes (f) + 4 bytes (i) = 10 bytes
    'format_char_sequence': 'hfi',
    'endian_character': '<'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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
sample_pdf Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ishanchadha01/lightneus/models/renderer.py
code served (permissive licence) · get_code("dad6efeeea24fad9")
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

torch.manual_seed(0)

# bins: tensor of bin edges, shape (batch, n_bins)
bins = torch.linspace(0, 1, steps=5).unsqueeze(0).expand(2, 5)

# weights: tensor of weights for each bin, shape (batch, n_bins-1)
weights = torch.rand(2, 4)

# n_samples: number of samples to draw
n_samples = 3

# det: whether to use deterministic sampling
det = False

ARGS = {
    "bins": bins,
    "weights": weights,
    "n_samples": n_samples,
    "det": det,
}
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
sdf_to_alpha Ran
ran; our contract draft was wrong, not the code
ventusff/neurecon/models/frameworks/neus.py
code served (permissive licence) · get_code("7bf297619343c144")
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 torch

torch.manual_seed(0)

# Create a small SDF tensor with shape (batch=2, steps=4)
# The function indexes as sdf[..., :-1] and sdf[..., 1:], so we need at least 2 elements in the last dimension
sdf = torch.randn(2, 4)

# s is a scalar parameter used in the sigmoid function
s = 10.0

ARGS = {
    "sdf": sdf,
    "s": s,
}
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 — 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
sdf_to_w Ran
ran; our contract draft was wrong, not the code
ventusff/neurecon/models/frameworks/neus.py
code served (permissive licence) · get_code("caee1b0439b2c3e5")
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 torch

torch.manual_seed(0)

# sdf_to_w expects:
# - sdf: torch.Tensor (signed distance field)
# - s: scalar (scaling parameter)

# Create a small SDF tensor with batch dimension and sequence dimension
# Shape: (batch=2, sequence=4)
sdf = torch.randn(2, 4)

# Create a scalar parameter s
s = 1.0

ARGS = {
    "sdf": sdf,
    "s": s,
}
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 — 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
synthesize_views Ran
ran on a synthesized input
sanowar-raihan/meta-neus/vis/object_rendering.py
code served (permissive licence) · get_code("9eef5b142b6f34a7")
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 int, shape (2, 4, 5, 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)

# Configuration dict - needs 'test_batchsize' key
conf = {
    'test_batchsize': 2
}

# Small model that takes ray origins and directions and outputs color
class SimpleRayModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(6, 3)  # 3 for ray_o + 3 for ray_d -> 3 for RGB color
    
    def forward(self, rays_o, rays_d):
        # rays_o: (batch, 3)
        # rays_d: (batch, 3)
        combined = torch.cat([rays_o, rays_d], dim=-1)  # (batch, 6)
        color = torch.sigmoid(self.fc(combined))  # (batch, 3)
        return {'color': color}

model = SimpleRayModel()

# Intrinsics: H, W, focal
H = 4
W = 5
focal = 6.0
instrinsics = (H, W, focal)

# Poses: (num_poses, 4, 4) camera extrinsic matrices
# We need num_poses such that total rays = H*W*num_poses is divisible by test_batchsize
# H=4, W=5, so H*W=20. With num_poses=2, total rays=40, which is divisible by test_batchsize=2
num_poses = 2
poses = torch.eye(4).unsqueeze(0).repeat(num_poses, 1, 1)
# Perturb them slightly so they're different
poses[1, 0, 3] = 0.5
poses[1, 1, 3] = 0.3

device = 'cpu'

ARGS = {
    'conf': conf,
    'model': model,
    'instrinsics': instrinsics,
    'poses': poses,
    'device': device
}
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 int, shape (2, 4, 5, 3) — shape (2, 4, 5, 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
load_data Not yet run
unverified (harvested, no recorded run)
Totoro97/NeuS/preprocess_custom_data/colmap_preprocess/pose_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Advanced-Vision-and-Learning-Lab/sparse-view-3dgs-pack, is pointer only (licence: NONE) · get_code("a3e32109361b1697")
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 Advanced-Vision-and-Learning-Lab/sparse-view-3dgs-pack, 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.

minify_v0 Not yet run
unverified (harvested, no recorded run)
Totoro97/NeuS/preprocess_custom_data/colmap_preprocess/pose_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Advanced-Vision-and-Learning-Lab/sparse-view-3dgs-pack, is pointer only (licence: NONE) · get_code("567061f23c36a283")
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 Advanced-Vision-and-Learning-Lab/sparse-view-3dgs-pack, 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 11 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 11 later) and 5 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_next_bytes 70 other papers
6 dated earlier, 64 later
1804.00650 (2018-04)
DeepMVS: Learning Multi-view Stereopsis
1902.10556 (2019-02)
Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
and 67 more not named here
read_cameras_text 37 other papers
5 dated earlier, 32 later
1902.10556 (2019-02)
Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
1912.11744 (2019-12)
Planar Prior Assisted PatchMatch Multi-View Stereo
and 34 more not named here
get_embedder 22 other papers
1 the same month, 21 later · 3 only as an assembly brick
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
2206.00665 (2022-06)
MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
and 19 more not named here
read_cameras_binary 21 other papers
5 dated earlier, 16 later
1902.10556 (2019-02)
Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
1912.11744 (2019-12)
Planar Prior Assisted PatchMatch Multi-View Stereo
and 18 more not named here
load_K_Rt_from_P 14 other papers
14 later
2201.05989 (2022-01)
Instant neural graphics primitives with a multiresolution hash encoding
2205.15848 (2022-05)
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction
2206.13597 (2022-06)
NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors
and 11 more not named here
extract_fields 8 other papers
8 later
2205.15848 (2022-05)
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction
2206.13597 (2022-06)
NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors
2211.11320 (2022-11)
Recovering Fine Details for Neural Implicit Surface Reconstruction
and 5 more not named here
sample_pdf 6 other papers
6 later
2206.13597 (2022-06)
NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors
2303.17968 (2023-03)
VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization
and 3 more not named here
cdf_Phi_s 1 other paper
1 later
2303.08605 (2023-03)
RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction
load_data 1 other paper
1 later
2601.17185 (2026-01)
LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction
minify_v0 1 other paper
1 later
2601.17185 (2026-01)
LGDWT-GS: Local and Global Discrete Wavelet-Regularized 3D Gaussian Splatting for Sparse-View Scene Reconstruction
sdf_to_alpha 1 other paper
1 later
2303.08605 (2023-03)
RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

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 novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision, easily get trapped in local minima, and therefore struggle with the reconstruction of objects with severe self-occlusion or thin structures. Meanwhile, recent neural methods for novel view synthesis, such as NeRF and its variants, use volume rendering to produce a neural scene representation with robustness of optimization, even for highly complex objects. However, extracting high-quality surfaces from this learned implicit representation is difficult because there are not sufficient surface constraints in the representation. In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation. We observe that the conventional volume rendering method causes inherent geometric errors (i.e. bias) for surface reconstruction, and therefore propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision. Experiments on the DTU dataset and the BlendedMVS dataset show that NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.

For agents

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

get_harvested_code_for_paper("2106.10689")
get_code_for_paper("2106.10689")
have("2106.10689")

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

curl https://syntology.ai/api/ran/2106.10689.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.10689.svg)](https://syntology.ai/paper/2106.10689)

Connect an agent — have() is free.