SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.12266 · CVPR · 2021

Deep Implicit Moving Least-Squares Functions for 3D Reconstruction

Yang Liu, Xin Tong, Hao Pan, Peng-Shuai Wang, Shi-Lin Liu, Hao-Xiang Guo

arXiv · PDF · Open in the Atlas

Code that ran

6 of 14 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 6 have no contract verdict; 0 failures of our instrument; 8 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/2103.12266.json · badge: /api/ran/2103.12266.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
Andy97/DeepMLS canonical (classifier label)
classifier basis: census
6 ran · 8 no recorded run
FunctionStatusWhere it lives
DoubleList_to_Bytes Ran
ran on a synthesized input
Andy97/DeepMLS/points3d-tf/pointsdataset/points_dataset_octreed7.py
code served (permissive licence) · get_code("6b9c5e67950491d0")
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 bytes. 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

# The function takes a float_list parameter and converts it to a numpy array
# of float64 dtype, then returns the bytes representation.
# We need to provide a list of floats (or something that can be converted to one).

ARGS = {
    "float_list": [1.5, 2.7, 3.14, 4.0, 5.5, 6.2]
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
Float32List_to_Bytes Ran
ran on a synthesized input
Andy97/DeepMLS/points3d-tf/pointsdataset/points_dataset_octreed7.py
code served (permissive licence) · get_code("cfa1ab3b87f65878")
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 bytes. 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

ARGS = {
    "float_list": [1.5, 2.5, 3.5, 4.5, 5.5]
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
IntList_to_Bytes Ran
ran on a synthesized input
Andy97/DeepMLS/points3d-tf/pointsdataset/points_dataset_octreed7.py
code served (permissive licence) · get_code("135b89fc9605f85a")
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 bytes. 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

ARGS = {
    "int_list": [1, 2, 3, 4, 5]
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
average_gradient Ran
ran on a synthesized input
Andy97/DeepMLS/utils.py
code served (permissive licence) · get_code("22b0391dbc9591fe")
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 list. 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 tensorflow as tf
import numpy as np

# Set random seed for reproducibility
tf.random.set_seed(0)

# Create mock gradient and variable pairs for multiple towers
# tower_grads should be a list of lists where each inner list contains (gradient, variable) tuples

# Create some sample variables (these would normally be model parameters)
var1 = tf.Variable(tf.ones([4, 3]), trainable=True)
var2 = tf.Variable(tf.ones([5, 2]), trainable=True)

# Create gradients for each variable (same shape as variables)
grad1_tower1 = tf.ones([4, 3])
grad1_tower2 = tf.ones([4, 3]) * 2

grad2_tower1 = tf.ones([5, 2])
grad2_tower2 = tf.ones([5, 2]) * 2

# Build tower_grads as a list of lists of (gradient, variable) tuples
# Each tower is a list of (grad, var) pairs
tower_grads = [
    [(grad1_tower1, var1), (grad2_tower1, var2)],  # Tower 0
    [(grad1_tower2, var1), (grad2_tower2, var2)],  # Tower 1
]

ARGS = {
    "tower_grads": tower_grads
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
config_reader Ran
ran on a synthesized input
Andy97/DeepMLS/utils.py
code served (permissive licence) · get_code("259c9e2644534d0b")
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 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 json
import tempfile
import os

# Create a temporary JSON config file
config_dict = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "num_epochs": 10,
    "layers": [64, 128, 256]
}

with tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False) as f:
    json.dump(config_dict, f)
    config_path = f.name

ARGS = {
    "config_path": config_path
}
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 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
rowwise_l2_norm_squared Ran
ran on a synthesized input
Andy97/DeepMLS/mls_marching_cubes.py
code served (permissive licence) · get_code("1767f3533c90fc34")
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 EagerTensor, ndim 1, dtype family float, shape (2,) 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 tensorflow as tf
import numpy as np

def rowwise_l2_norm_squared(feature):
    return tf.reduce_sum(tf.math.square(feature), axis=-1)

# Create a small tensor with shape (2, 4) - batch size 2, feature dimension 4
feature = tf.constant([[1.0, 2.0, 3.0, 4.0],
                       [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

ARGS = {
    "feature": feature
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
batch_norm Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/Octree/ocnn.py
code served (permissive licence) · get_code("489c5f27ae7ac730")
How it ran

no invocation recorded.

dense Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/Octree/ocnn.py
code served (permissive licence) · get_code("025d5ba4076f4507")
How it ran

no invocation recorded.

get_variables_with_name Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/Octree/ocnn.py
code served (permissive licence) · get_code("81a82eb551047ed3")
How it ran

no invocation recorded.

normal_unit_norm_regularization Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/DeepMLS_Generation.py
code served (permissive licence) · get_code("527c707a39fdee51")
How it ran

no invocation recorded.

octree_network_unet Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/network_architecture.py
code served (permissive licence) · get_code("13007f9c486275fe")
How it ran

no invocation recorded.

octree_network_unet_completion_decode_shape Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/network_architecture.py
code served (permissive licence) · get_code("01460b3f669373ad")
How it ran

no invocation recorded.

preprocess_octree_data_from_unoriented_points Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/network_architecture.py
code served (permissive licence) · get_code("84287e86ee7c75a5")
How it ran

no invocation recorded.

tf_summary_from_dict Not yet run
unverified (harvested, no recorded run)
Andy97/DeepMLS/utils.py
code served (permissive licence) · get_code("1a5ed5d936a5d8c3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 14 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

Point set is a flexible and lightweight representation widely used for 3D deep learning. However, their discrete nature prevents them from representing continuous and fine geometry, posing a major issue for learning-based shape generation. In this work, we turn the discrete point sets into smooth surfaces by introducing the well-known implicit moving least-squares (IMLS) surface formulation, which naturally defines locally implicit functions on point sets. We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces. Our IMLSNet predicts an octree structure as a scaffold for generating MLS points where needed and characterizes shape geometry with learned local priors. Furthermore, our implicit function evaluation is independent of the neural network once the MLS points are predicted, thus enabling fast runtime evaluation. Our experiments on 3D object reconstruction demonstrate that IMLSNets outperform state-of-the-art learning-based methods in terms of reconstruction quality and computational efficiency. Extensive ablation tests also validate our network design and loss functions.

For agents

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

get_harvested_code_for_paper("2103.12266")
get_code_for_paper("2103.12266")
have("2103.12266")

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

curl https://syntology.ai/api/ran/2103.12266.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.12266.svg)](https://syntology.ai/paper/2103.12266)

Connect an agent — have() is free.