SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.06340 · ECCV · 2022

SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data

Andrea Vedaldi, João Henriques, Dylan Campbell, Eldar Insafutdinov

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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 10 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2206.06340.json · badge: /api/ran/2206.06340.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
eldar/snes canonical (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
FunctionStatusWhere it lives
extract_fields Ran
ran on a synthesized input
eldar/snes/models/neus_renderer.py
code served (permissive licence) · get_code("d324c8b8074103c6")
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 3, dtype family float, shape (32, 32, 32) 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 numpy as np

torch.manual_seed(0)

# Define a simple query function that takes points and returns scalar values
def query_func(pts):
    """
    Simple query function that takes a tensor of points (N, 3) and returns (N,) values.
    The function uses the sum of coordinates as a dummy field value.
    """
    # pts shape: (N, 3)
    # return shape: (N,)
    return pts.sum(dim=-1)

# Define the arguments
ARGS = {
    "bound_min": [-1.0, -1.0, -1.0],
    "bound_max": [1.0, 1.0, 1.0],
    "resolution": 32,
    "query_func": query_func,
    "device": None,
}
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 ndarray, ndim 3, dtype family float, shape (32, 32, 32) — shape (32, 32, 32) 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 on a synthesized input
eldar/snes/models/renderer.py
code served (permissive licence) · get_code("f0fdd6a78b6cb562")
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 3, dtype family float, shape (4, 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 numpy as np

torch.manual_seed(0)

# Define a simple query function that takes points and returns scalar values
def query_func(pts):
    """
    Takes points of shape (N, 3) and returns scalar values of shape (N,).
    Simple function: sum of coordinates squared.
    """
    return (pts ** 2).sum(dim=-1)

# Define the arguments
bound_min = [-1.0, -1.0, -1.0]
bound_max = [1.0, 1.0, 1.0]
resolution = 4  # Small resolution for quick execution
device = None  # CPU only

ARGS = {
    "bound_min": bound_min,
    "bound_max": bound_max,
    "resolution": resolution,
    "query_func": query_func,
    "device": device,
}
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 ndarray, ndim 3, dtype family float, shape (4, 4, 4) — shape (4, 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
find_latest_checkpoint Ran
ran on a synthesized input
eldar/snes/exp_runner.py
code served (permissive licence) · get_code("67cbda99e73243e0")
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 str. 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 os
import tempfile
import shutil

# Create a temporary directory with some checkpoint files
temp_dir = tempfile.mkdtemp()

# Create some dummy .pth checkpoint files
checkpoint_files = [
    "checkpoint_001.pth",
    "checkpoint_010.pth",
    "checkpoint_005.pth",
    "checkpoint_015.pth",
]

for filename in checkpoint_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write("dummy checkpoint")

# Also create a non-.pth file to test filtering
non_pth_file = os.path.join(temp_dir, "readme.txt")
with open(non_pth_file, 'w') as f:
    f.write("not a checkpoint")

ARGS = {
    "ckpt_dir": temp_dir
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_embedder Ran
ran on a synthesized input
eldar/snes/models/embedder.py
code served (permissive licence) · get_code("41f4831e3edaa59f")
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. 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 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,
    'base_freq': 1.0
}
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
invert_intrinsics Ran
ran on a synthesized input
eldar/snes/models/camera.py
code served (permissive licence) · get_code("40c29839a410082e")
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 (2, 3, 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)

# K is a batch of intrinsic matrices
# The function indexes K with [:, 0, 0], [:, 1, 1], [:, 0, 2], [:, 1, 2]
# So K should have shape (batch_size, 3, 3)
batch_size = 2
K = torch.tensor([
    [[500.0, 0.0, 320.0],
     [0.0, 500.0, 240.0],
     [0.0, 0.0, 1.0]],
    [[600.0, 0.0, 160.0],
     [0.0, 600.0, 120.0],
     [0.0, 0.0, 1.0]]
], dtype=torch.float32)

ARGS = {
    "K": K
}
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 (2, 3, 3) — shape (2, 3, 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_auto_bbox_scale Ran
ran on a synthesized input
eldar/snes/models/dataset_co3d.py
code served (permissive licence) · get_code("4e7a35a1ddb7bc39")
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 os
from pathlib import Path
import numpy as np
import tempfile
import shutil

# Create a temporary directory structure for the mock data
temp_dir = tempfile.mkdtemp()
code_dir = temp_dir

# Create the directory structure that the function expects
category = "test_category"
instance = "test_instance"
data_extra_dir = Path(temp_dir) / "data_extra"
category_dir = data_extra_dir / category / instance
category_dir.mkdir(parents=True, exist_ok=True)

# Create a mock alignment.npy file
alignment_data = {
    'T': np.array([[1.0, 0.0, 0.0, 0.5],
                   [0.0, 1.0, 0.0, 0.5],
                   [0.0, 0.0, 1.0, 0.5],
                   [0.0, 0.0, 0.0, 1.0]], dtype=np.float32),
    'box_size': np.array([2.0, 3.0, 1.5], dtype=np.float32)
}
alignment_path = category_dir / "alignment.npy"
np.save(alignment_path, alignment_data)

# Create a mock config class
class MockConfig:
    def __init__(self):
        self.data_extra_dir = str(data_extra_dir)
        self.category = category
        self.instance = instance

# Monkey-patch the module-level code_dir to use our temp directory
import sys
import types
test_module = types.ModuleType('test_module')
test_module.code_dir = code_dir

cfg = MockConfig()
margin_scale = 1.5
apply_scaling = True

ARGS = {
    'cfg': cfg,
    'margin_scale': margin_scale,
    'apply_scaling': apply_scaling
}
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 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
mask_translation Ran
ran on a synthesized input
eldar/snes/models/transform.py
code served (permissive licence) · get_code("aad8f9c2126f4e0a")
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 minimal config structure with nested attributes
class RendererConfig:
    def __init__(self):
        self.symmetry_translation_1dof = False
        self.symmetry_translation_2dof = False

class ModelConfig:
    def __init__(self):
        self.renderer = RendererConfig()

class Config:
    def __init__(self):
        self.model = ModelConfig()

# Create config instance
cfg = Config()

# Create t_ as a small tensor (batch_size=2, features=3)
t_ = torch.randn(2, 3)

ARGS = {
    "cfg": cfg,
    "t_": t_
}
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
sample_pdf Ran
ran on a synthesized input
eldar/snes/models/neus_renderer.py
code served (permissive licence) · get_code("be7a4badf2fccf27")
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)

# bins: tensor of bin edges, shape (batch_size, num_bins)
# weights: tensor of weights, shape (batch_size, num_bins-1)
# n_samples: number of samples to draw
# det: whether to use deterministic sampling

batch_size = 2
num_bins = 5

bins = torch.linspace(0, 1, num_bins).unsqueeze(0).expand(batch_size, -1)
weights = torch.ones(batch_size, num_bins - 1)
n_samples = 4
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, 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
sample_pdf Ran
ran on a synthesized input
eldar/snes/models/renderer.py
code served (permissive licence) · get_code("d250b087de2b4587")
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 should be compatible with weights
# The function uses bins with shape matching the expand operation
# bins needs shape [batch_size, num_bins] where num_bins = num_weights + 1
bins = torch.linspace(0, 1, steps=5).unsqueeze(0).expand(2, 5)

# weights: tensor of weights for the PDF, shape [batch_size, num_weights]
# Used for normalization and PDF computation
weights = torch.ones(2, 4)

# n_samples: number of samples to draw
n_samples = 3

# det: deterministic flag (boolean)
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
to_global_path Ran
ran on a synthesized input
eldar/snes/models/dataset_co3d.py
code served (permissive licence) · get_code("995f2c25a95ec737")
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 PosixPath. 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 os
from pathlib import Path
import tempfile

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create a test file to ensure path.exists() works
test_file = Path(temp_dir) / "test.txt"
test_file.write_text("test content")

# Test with both an existing path and a non-existing relative path
ARGS = {
    "path": str(test_file)  # Use the path to the test file we created
}
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 PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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
dataset_factory Not yet run
unverified (harvested, no recorded run)
eldar/snes/models/factory.py
code served (permissive licence) · get_code("bba66013ef0953e1")
How it ran

no invocation recorded.

load_datasets Not yet run
unverified (harvested, no recorded run)
eldar/snes/models/factory.py
code served (permissive licence) · get_code("d7d5462dbe2c1f44")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 10 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 10 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 a method for the accurate 3D reconstruction of partly-symmetric objects. We build on the strengths of recent advances in neural reconstruction and rendering such as Neural Radiance Fields (NeRF). A major shortcoming of such approaches is that they fail to reconstruct any part of the object which is not clearly visible in the training image, which is often the case for in-the-wild images and videos. When evidence is lacking, structural priors such as symmetry can be used to complete the missing information. However, exploiting such priors in neural rendering is highly non-trivial: while geometry and non-reflective materials may be symmetric, shadows and reflections from the ambient scene are not symmetric in general. To address this, we apply a soft symmetry constraint to the 3D geometry and material properties, having factored appearance into lighting, albedo colour and reflectivity. We evaluate our method on the recently introduced CO3D dataset, focusing on the car category due to the challenge of reconstructing highly-reflective materials. We show that it can reconstruct unobserved regions with high fidelity and render high-quality novel view images.

For agents

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

get_harvested_code_for_paper("2206.06340")
get_code_for_paper("2206.06340")
have("2206.06340")

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

curl https://syntology.ai/api/ran/2206.06340.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.06340.svg)](https://syntology.ai/paper/2206.06340)

Connect an agent — have() is free.