SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.00758 · 2018

Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures of our instrument; 0 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/1808.00758.json · badge: /api/ran/1808.00758.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
Yang7879/AttSets canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
read_as_3d_array Ran
ran; our contract draft was wrong, not the code
Yang7879/AttSets/binvox_rw.py
code served (permissive licence) · get_code("2021d2aec4546384")
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 Voxels. 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 numpy as np
import io

# Create a minimal binary binvox format in memory
def create_test_binvox_file():
    """Create a minimal valid binvox file in memory."""
    fp = io.BytesIO()
    
    # Write header
    fp.write(b'#binvox 1\n')
    fp.write(b'dim 4 4 4\n')
    fp.write(b'translate 0.0 0.0 0.0\n')
    fp.write(b'scale 1.0\n')
    fp.write(b'data\n')
    
    # Write minimal voxel data (64 bytes for 4x4x4)
    # Run-length encoded: alternating value and count
    # Start with all False (0) for first 32, then all True (1) for last 32
    fp.write(bytes([0, 32]))  # 32 False values
    fp.write(bytes([1, 32]))  # 32 True values
    
    fp.seek(0)
    return fp

fp = create_test_binvox_file()
fix_coords = True

ARGS = {
    'fp': fp,
    'fix_coords': fix_coords
}
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 Voxels — a Voxels output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Voxels 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_as_coord_array Ran
ran; our contract draft was wrong, not the code
Yang7879/AttSets/binvox_rw.py
code served (permissive licence) · get_code("74e08d52a8b6e172")
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 Voxels. 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 numpy as np
from io import BytesIO

# Create a minimal binvox file in memory
def create_binvox_bytes():
    """Create a valid binvox format byte stream"""
    fp = BytesIO()
    
    # Write header
    fp.write(b'#binvox 1\n')
    fp.write(b'dim 4 4 4\n')
    fp.write(b'translate 0.0 0.0 0.0\n')
    fp.write(b'scale 1.0\n')
    fp.write(b'data\n')
    
    # Write simple voxel data (alternating 0s and 1s with counts)
    # 64 voxels total in 4x4x4 grid
    # Encode as: value(0/1), count, value, count, ...
    fp.write(bytes([0, 32]))  # 32 empty voxels
    fp.write(bytes([1, 16]))  # 16 filled voxels
    fp.write(bytes([0, 16]))  # 16 empty voxels
    
    fp.seek(0)
    return fp

# Create the file pointer with valid binvox data
fp = create_binvox_bytes()

ARGS = {
    'fp': fp,
    'fix_coords': 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 Voxels — a Voxels output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Voxels 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_header Ran
ran; our contract draft was wrong, not the code
Yang7879/AttSets/binvox_rw.py
code served (permissive licence) · get_code("ba966c4838f2c939")
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. 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 io

# Create a mock binvox file content in memory
binvox_content = b"""#binvox 1
dim 64 64 64
translate 0.0 0.0 0.0
scale 1.0
data
"""

# Create a BytesIO object that acts like a file pointer
fp = io.BytesIO(binvox_content)

ARGS = {
    'fp': fp
}
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 — 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 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
read_header 6 other papers
1 dated earlier, 5 later
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1901.11153 (2019-01)
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
2003.12397 (2020-03)
Modeling 3D Shapes by Reinforcement Learning
and 3 more not named here
read_as_3d_array 5 other papers
1 dated earlier, 4 later
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1901.11153 (2019-01)
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
2003.12397 (2020-03)
Modeling 3D Shapes by Reinforcement Learning
and 2 more not named here
read_as_coord_array 5 other papers
1 dated earlier, 4 later
1607.07539 (2016-07)
Semantic Image Inpainting with Deep Generative Models
1901.11153 (2019-01)
Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
2003.12397 (2020-03)
Modeling 3D Shapes by Reinforcement Learning
and 2 more not named here

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 study the problem of recovering an underlying 3D shape from a set of images. Existing learning based approaches usually resort to recurrent neural nets, e.g., GRU, or intuitive pooling operations, e.g., max/mean poolings, to fuse multiple deep features encoded from input images. However, GRU based approaches are unable to consistently estimate 3D shapes given different permutations of the same set of input images as the recurrent unit is permutation variant. It is also unlikely to refine the 3D shape given more images due to the long-term memory loss of GRU. Commonly used pooling approaches are limited to capturing partial information, e.g., max/mean values, ignoring other valuable features. In this paper, we present a new feed-forward neural module, named AttSets, together with a dedicated training algorithm, named FASet, to attentively aggregate an arbitrarily sized deep feature set for multi-view 3D reconstruction. The AttSets module is permutation invariant, computationally efficient and flexible to implement, while the FASet algorithm enables the AttSets based network to be remarkably robust and generalize to an arbitrary number of input images. We thoroughly evaluate FASet and the properties of AttSets on multiple large public datasets. Extensive experiments show that AttSets together with FASet algorithm significantly outperforms existing aggregation approaches.

For agents

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

get_harvested_code_for_paper("1808.00758")
get_code_for_paper("1808.00758")
have("1808.00758")

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

curl https://syntology.ai/api/ran/1808.00758.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.00758.svg)](https://syntology.ai/paper/1808.00758)

Connect an agent — have() is free.