SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.12250 · 2020

Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

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; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2006.12250.json · badge: /api/ran/2006.12250.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
hzxie/Pix2Vox canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
count_parameters Ran
ran, honoured the contract we drafted
hzxie/Pix2Vox/utils/network_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from sleepymalc/miss, is pointer only (licence: NONE) · get_code("df23da82fbd7ff7b")
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 sleepymalc/miss, 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_as_3d_array Ran
ran on a synthesized input
hzxie/Pix2Vox/utils/binvox_rw.py
code served (permissive licence) · get_code("fdd34323213bcdbf")
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 binvox file in memory
def create_binvox_buffer():
    """Create a valid binvox file buffer for testing."""
    buffer = io.BytesIO()
    
    # Write header
    buffer.write(b'#binvox 1\n')
    buffer.write(b'dim 4 4 4\n')
    buffer.write(b'translate 0.0 0.0 0.0\n')
    buffer.write(b'scale 1.0\n')
    buffer.write(b'data\n')
    
    # Write voxel data (run-length encoded)
    # Create a simple pattern: 32 zeros, 32 ones (for a 4x4x4 = 64 voxel grid)
    buffer.write(bytes([0, 32]))  # 32 zeros
    buffer.write(bytes([1, 32]))  # 32 ones
    
    buffer.seek(0)
    return buffer

# Create the file pointer
fp = create_binvox_buffer()

# Define arguments for read_as_3d_array
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_as_coord_array Ran
ran on a synthesized input
hzxie/Pix2Vox/utils/binvox_rw.py
code served (permissive licence) · get_code("873e9e9846a73a89")
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 binvox file in memory
def create_binvox_bytes():
    """Create a valid binvox file as bytes"""
    header = b'#binvox 1\n'
    header += b'dim 4 4 4\n'
    header += b'translate 0.0 0.0 0.0\n'
    header += b'scale 1.0\n'
    header += b'data\n'
    
    # Create simple run-length encoded data
    # For a 4x4x4 voxel grid = 64 voxels total
    # Let's create: 32 empty (0), 16 filled (1), 16 empty (0)
    data = bytes([0, 32, 1, 16, 0, 16])
    
    return header + data

# Create a file-like object
binvox_fp = io.BytesIO(create_binvox_bytes())

ARGS = {
    'fp': binvox_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 on a synthesized input
hzxie/Pix2Vox/utils/binvox_rw.py
code served (permissive licence) · get_code("e2daca6af10fd133")
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 io

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

fp = io.BytesIO(binvox_content)

ARGS = {
    'fp': fp
}
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 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
var_or_cuda Ran
ran, honoured the contract we drafted
hzxie/Pix2Vox/utils/network_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xy-boy/blind-satellite-vsr, is pointer only (licence: NONE) · get_code("6b1ad2156e46dae6")
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 xy-boy/blind-satellite-vsr, 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_volume_views Not yet run
unverified (harvested, no recorded run)
hzxie/Pix2Vox/utils/binvox_visualization.py
code served (permissive licence) · get_code("c899e4fcf0ff9c5b")
How it ran

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, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 5 later) and 1 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
count_parameters 7 other papers
3 dated earlier, 4 later
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
1904.12257 (2019-04)
Spatio-Temporal Filter Adaptive Network for Video Deblurring
1905.05934 (2019-05)
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
and 4 more not named here
var_or_cuda 4 other papers
1 dated earlier, 1 the same month, 2 later
1904.12257 (2019-04)
Spatio-Temporal Filter Adaptive Network for Video Deblurring
2006.03761 (2020-06)
GRNet: Gridding Residual Network for Dense Point Cloud Completion
2207.10852 (2022-07)
Spatio-Temporal Deformable Attention Network for Video Deblurring
and 1 more not named here
read_as_3d_array 1 other paper
1 later
2106.12102 (2021-06)
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
read_as_coord_array 1 other paper
1 later
2106.12102 (2021-06)
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
read_header 1 other paper
1 later
2106.12102 (2021-06)
LegoFormer: Transformers for Block-by-Block Multi-view 3D 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

Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) to sequentially fuse feature maps of input images. However, RNN-based approaches are unable to produce consistent reconstruction results when given the same input images with different orders. Moreover, RNNs may forget important features from early input images due to long-term memory loss. To address these issues, we propose a novel framework for single-view and multi-view 3D object reconstruction, named Pix2Vox++. By using a well-designed encoder-decoder, it generates a coarse 3D volume from each input image. A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume. To further correct the wrongly recovered parts in the fused 3D volume, a refiner is adopted to generate the final output. Experimental results on the ShapeNet, Pix3D, and Things3D benchmarks show that Pix2Vox++ performs favorably against state-of-the-art methods in terms of both accuracy and efficiency.

For agents

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

get_harvested_code_for_paper("2006.12250")
get_code_for_paper("2006.12250")
have("2006.12250")

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

curl https://syntology.ai/api/ran/2006.12250.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.12250.svg)](https://syntology.ai/paper/2006.12250)

Connect an agent — have() is free.